While Neural Machine Translation (NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we humans encounter an unknown entity during translation, we usually first look up in a dictionary and then organize the entity translation together with the translations of other parts to form a smooth target sentence. Inspired by this translation process, we propose an Extract-and-Attend approach to enhance entity translation in NMT, where the translation candidates of source entities are first extracted from a dictionary and then attended to by the NMT model to generate the target sentence. Specifically, the translation candidates are extracted by first detecting the entities in a source sentence and then translating the entities through looking up in a dictionary. Then, the extracted candidates are added as a prefix of the decoder input to be attended to by the decoder when generating the target sentence through self-attention. Experiments conducted on En-Zh and En-Ru demonstrate that the proposed method is effective on improving both the translation accuracy of entities and the overall translation quality, with up to 35% reduction on entity error rate and 0.85 gain on BLEU and 13.8 gain on COMET.

This paper rethinks translation memory augmented neural machine translation (TM-augmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variance-bias decomposition principle. The finding demonstrates that TM-augmented NMT is good at the ability of fitting data (i.e., lower bias) but is more sensitive to the fluctuations in the training data (i.e., higher variance), which provides an explanation to a recently reported contradictory phenomenon on the same translation task: TM-augmented NMT substantially advances NMT without TM under the high resource scenario whereas it fails under the low resource scenario. Then this paper proposes a simple yet effective TM-augmented NMT model to promote the variance and address the contradictory phenomenon. Extensive experiments show that the proposed TM-augmented NMT achieves consistent gains over both conventional NMT and existing TM-augmented NMT under two variance-preferable (low resource and plug-and-play) scenarios as well as the high resource scenario.

Federated learning involves collaborative training with private data from multiple platforms, while not violating data privacy. We study the problem of federated domain adaptation for Named Entity Recognition (NER), where we seek to transfer knowledge across different platforms with data of multiple domains. In addition, we consider a practical and challenging scenario, where NER datasets of different platforms of federated learning are annotated with heterogeneous tag sets, i.e., different sets of entity types. The goal is to train a global model with federated learning, such that it can predict with a complete tag set, i.e., with all the occurring entity types for data across all platforms. To cope with the heterogeneous tag sets in a multi-domain setting, we propose a distillation approach along with a mechanism of instance weighting to facilitate knowledge transfer across platforms. Besides, we release two re-annotated clinic NER datasets, for testing the proposed method in the clinic domain. Our method shows superior empirical performance for NER with federated learning.

Contrastive learning has been widely studied in sentence representation learning. However, earlier works mainly focus on the construction of positive examples, while in-batch samples are often simply treated as negative examples. This approach overlooks the importance of selecting appropriate negative examples, potentially leading to a scarcity of hard negatives and the inclusion of false negatives. To address these issues, we propose ClusterNS (Clustering-aware Negative Sampling), a novel method that incorporates cluster information into contrastive learning for unsupervised sentence representation learning. We apply a modified K-means clustering algorithm to supply hard negatives and recognize in-batch false negatives during training, aiming to solve the two issues in one unified framework. Experiments on semantic textual similarity (STS) tasks demonstrate that our proposed ClusterNS compares favorably with baselines in unsupervised sentence representation learning. Our code has been made publicly available at github.com/djz233/ClusterNS.

Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars. However, current multimodal models have reached a performance bottleneck. To investigate the causes of this problem, we perform extensive empirical evaluation and in-depth analysis of the datasets to answer the following questions: **Q1**: Are the modalities equally important for TMSC? **Q2**: Which multimodal fusion modules are more effective? **Q3**: Do existing datasets adequately support the research? Our experiments and analyses reveal that the current TMSC systems primarily rely on the textual modality, as most of targets’ sentiments can be determined *solely* by text. Consequently, we point out several directions to work on for the TMSC task in terms of model design and dataset construction. The code and data can be found in https://github.com/Junjie-Ye/RethinkingTMSC.

The use of visually-rich documents in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers. Unfortunately, the lack of appropriate datasets has significantly hindered advancements in the field. To address this issue, we introduce DocTrack, a visually-rich document dataset really aligned with human eye-movement information using eye-tracking technology. This dataset can be used to investigate the challenges mentioned above. Additionally, we explore the impact of human reading order on document understanding tasks and examine what would happen if a machine reads in the same order as a human. Our results suggest that although Document AI models have made significant progresses, they still have a long way to go before they can read visually richer documents as accurately, continuously, and flexibly as humans do. These findings have potential implications for future research and development of document intelligence.

Opinion summarization is expected to digest larger review sets and provide summaries from different perspectives. However, most existing solutions are deficient in epitomizing extensive reviews and offering opinion summaries from various angles due to the lack of designs for information selection. To this end, we propose SubSumm, a supervised summarization framework for large-scale multi-perspective opinion summarization. SubSumm consists of a review sampling strategy set and a two-stage training scheme. The sampling strategies take sentiment orientation and contrastive information value into consideration, with which the review subsets from different perspectives and quality levels can be selected. Subsequently, the summarizer is encouraged to learn from the sub-optimal and optimal subsets successively in order to capitalize on the massive input. Experimental results on AmaSum and Rotten Tomatoes datasets demonstrate that SubSumm is adept at generating pros, cons, and verdict summaries from hundreds of input reviews. Furthermore, our in-depth analysis verifies that the advanced selection of review subsets and the two-stage training scheme are vital to boosting the summarization performance.

Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through chain of thought (CoT) prompting. Recently, there has been a growing interest in transferring these reasoning abilities from LLMs to smaller models. However, achieving both the diversity and consistency in rationales presents a challenge. In this paper, we focus on enhancing these two aspects and propose Multi-CoT Consistent Knowledge Distillation (MCC-KD) to efficiently distill the reasoning capabilities. In MCC-KD, we generate multiple rationales for each question and enforce consistency among their predictions by minimizing the bidirectional KL-divergence between the answer distributions. We conduct comprehensive experiments to investigate the effectiveness of MCC-KD with different model architectures (LLaMA/FlanT5) and various model scales (3B/7B/11B/13B) on both mathematical reasoning and commonsense reasoning benchmarks. The empirical results demonstrate that MCC-KD achieves superior performance on in-distribution datasets and exhibits a strong generalization ability on out-of-distribution datasets.

Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue models fail to accurately express the external factual knowledge they rely upon. Inspired by previous work which identified that feedforward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability of FFNs by knowledge enhancement and alignment respectively. We first propose K-Dial, which explicitly introduces extended FFNs in Transformers to enhance factual knowledge expressions given the specific patterns of knowledge-grounded dialogue inputs. Additionally, we apply the reinforcement learning for factual consistency (RLFC) method to implicitly adjust FFNs’ expressions in responses by aligning with gold knowledge for the factual consistency preference. To comprehensively assess the factual consistency and dialogue quality of responses, we employ extensive automatic measures and human evaluations including sophisticated fine-grained NLI-based metrics. Experimental results on WoW and CMU_DoG datasets demonstrate that our methods efficiently enhance the ability of the FFN module to convey factual knowledge, validating the efficacy of improving factual consistency for knowledge-grounded dialogue systems.

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.

Large Language Models (LLMs), such as ChatGPT, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user’s hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (Cue-CoT), which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue, aiming to provide a more personalized and engaging response. To evaluate the approach, we build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English, targeting 3 major linguistic cues during the conversation: personality, emotion, and psychology. We conducted experiments on the proposed benchmark with 5 LLMs under both zero-shot and one-shot settings. Empirical results demonstrate our proposed Cue-CoT method outperforms standard prompting methods in terms of both helpfulness and acceptability on all datasets.

The decoding algorithm is critical for open-ended text generation, transforming latent representations into coherent and meaningful outputs. This paper investigates the self-reinforcement effect in text generation and the effectiveness of a repetition penalty to mitigate it. However, determining the optimal repetition penalty value is challenging. To tackle this, we propose a forgetting mechanism that disregards distant tokens, reducing the burden of penalty selection. In addition, we introduce a length penalty to address overly short sentences caused by excessive penalties. Our penalty decoding approach incorporating three strategies helps resolve issues with sampling methods deviating from factual information. Experimental results demonstrate the efficacy of our approach in generating high-quality sentences resembling human output.

Word-level auto-completion (WLAC) plays a crucial role in Computer-Assisted Translation. While previous studies have primarily focused on designing complex model architectures, this paper takes a different perspective by rethinking the fundamental question: what kind of words are good auto-completions? We introduce a measurable criterion to address this question and discover that existing WLAC models often fail to meet this criterion. Building upon this observation, we propose an effective approach to enhance WLAC performance by promoting adherence to the criterion. Notably, the proposed approach is general and can be applied to various encoder-based architectures. Through extensive experiments, we demonstrate that our approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022, while utilizing significantly smaller model sizes.

Nearest Neighbor Machine Translation (kNN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons underlying its success have not been thoroughly investigated. In this paper, we comprehensively analyze kNN-MT through theoretical and empirical studies. Initially, we provide new insights into the working mechanism of kNN-MT as an efficient technique to implicitly execute gradient descent on the output projection layer of NMT, indicating that it is a specific case of model fine-tuning. Subsequently, we conduct multi-domain experiments and word-level analysis to examine the differences in performance between kNN-MT and entire-model fine-tuning. Our findings suggest that: (i) Incorporating kNN-MT with adapters yields comparable translation performance to fine-tuning on in-domain test sets, while achieving better performance on out-of-domain test sets; (ii) Fine-tuning significantly outperforms kNN-MT on the recall of in-domain low-frequency words, but this gap could be bridged by optimizing the context representations with additional adapter layers.

Extracting meaningful entities belonging to predefined categories from Visually-rich Form-like Documents (VFDs) is a challenging task. Visual and layout features such as font, background, color, and bounding box location and size provide important cues for identifying entities of the same type. However, existing models commonly train a visual encoder with weak cross-modal supervision signals, resulting in a limited capacity to capture these non-textual features and suboptimal performance. In this paper, we propose a novel Visually-Asymmetric coNsistenCy Learning (VANCL) approach that addresses the above limitation by enhancing the model’s ability to capture fine-grained visual and layout features through the incorporation of color priors. Experimental results on benchmark datasets show that our approach substantially outperforms the strong LayoutLM series baseline, demonstrating the effectiveness of our approach. Additionally, we investigate the effects of different color schemes on our approach, providing insights for optimizing model performance. We believe our work will inspire future research on multimodal information extraction.

Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models’ knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.

Knowledge distillation has attracted a great deal of interest recently to compress large language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the teacher’s behavior while ignoring the reasoning behind it. Second, these methods usually focus on the transfer of sophisticated model-specific knowledge but overlook data-specific knowledge. In this paper, we present a novel attribution-driven knowledge distillation approach, which explores the token-level rationale behind the teacher model based on Integrated Gradients (IG) and transfers attribution knowledge to the student model. To enhance the knowledge transfer of model reasoning and generalization, we further explore multi-view attribution distillation on all potential decisions of the teacher. Comprehensive experiments are conducted with BERT on the GLUE benchmark. The experimental results demonstrate the superior performance of our approach to several state-of-the-art methods.

Automatic summarization generates concise summaries that contain key ideas of source documents. As the most mainstream datasets for the news sub-domain, CNN/DailyMail and BBC XSum have been widely used for performance benchmarking. However, the reference summaries of those datasets turn out to be noisy, mainly in terms of factual hallucination and information redundancy. To address this challenge, we first annotate new expert-writing Element-aware test sets following the “Lasswell Communication Model” proposed by Lasswell, allowing reference summaries to focus on more fine-grained news elements objectively and comprehensively. Utilizing the new test sets, we observe the surprising zero-shot summary ability of LLMs, which addresses the issue of the inconsistent results between human preference and automatic evaluation metrics of LLMs’ zero-shot summaries in prior work. Further, we propose a Summary Chain-of-Thought (SumCoT) technique to elicit LLMs to generate summaries step by step, which helps them integrate more fine-grained details of source documents into the final summaries that correlate with the human writing mindset. Experimental results show our method outperforms state-of-the-art fine-tuned PLMs and zero-shot LLMs by +4.33/+4.77 in ROUGE-L on the two datasets, respectively. Dataset and code are publicly available at https://github.com/Alsace08/SumCoT.

Training grounded response generation models often requires a large collection of grounded dialogues. However, it is costly to build such dialogues. In this paper, we present a synthetic data generation framework (SynDG) for grounded dialogues. The generation process utilizes large pre-trained language models and freely available knowledge data (e.g., Wikipedia pages, persona profiles, etc.). The key idea of designing SynDG is to consider dialogue flow and coherence in the generation process. Specifically, given knowledge data, we first heuristically determine a dialogue flow, which is a series of knowledge pieces. Then, we employ T5 to incrementally turn the dialogue flow into a dialogue. To ensure coherence of both the dialogue flow and the synthetic dialogue, we design a two-level filtering strategy, at the flow-level and the utterance-level respectively. Experiments on two public benchmarks show that the synthetic grounded dialogue data produced by our framework is able to significantly boost model performance in both full training data and low-resource scenarios.

Tense inconsistency frequently occurs in machine translation. However, there are few criteria to assess the model’s mastery of tense prediction from a linguistic perspective. In this paper, we present a parallel tense test set, containing French-English 552 utterances. We also introduce a corresponding benchmark, tense prediction accuracy. With the tense test set and the benchmark, researchers are able to measure the tense consistency performance of machine translation systems for the first time.

Word-level auto-completion (WLAC) plays a crucial role in Computer-Assisted Translation. In this paper, we describe the SJTU-MTLAB’s submission to the WMT23 WLAC task. We propose a joint method to incorporate the machine translation task to the WLAC task. The proposed approach is general and can be applied to various encoder-based architectures. Through extensive experiments, we demonstrate that our approach can greatly improve performance, while maintaining significantly small model sizes.

This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task. We participate in the text-to-text and speech-to-text simultaneous translation from English to Mandarin Chinese. The training of the CAAT is improved by training across multiple values of right context window size, which achieves good online performance without setting a prior right context window size for training. For speech-to-text task, the best model we submitted achieves 25.87, 26.21, 26.45 BLEU in low, medium and high regimes on tst-COMMON, corresponding to 27.94, 28.31, 28.43 BLEU in text-to-text task.

Previous work of class-incremental learning for Named Entity Recognition (NER) relies on the assumption that there exists abundance of labeled data for the training of new classes. In this work, we study a more challenging but practical problem, i.e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones. To alleviate the problem of catastrophic forgetting in few-shot class-incremental learning, we reconstruct synthetic training data of the old classes using the trained NER model, augmenting the training of new classes. We further develop a framework that distills from the existing model with both synthetic data, and real data from the current training set. Experimental results show that our approach achieves significant improvements over existing baselines.

Multimodal Entity Linking (MEL) which aims at linking mentions with multimodal contexts to the referent entities from a knowledge base (e.g., Wikipedia), is an essential task for many multimodal applications. Although much attention has been paid to MEL, the shortcomings of existing MEL datasets including limited contextual topics and entity types, simplified mention ambiguity, and restricted availability, have caused great obstacles to the research and application of MEL. In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base. A well-tailored annotation procedure is adopted to ensure the quality of the dataset. Based on WikiDiverse, a sequence of well-designed MEL models with intra-modality and inter-modality attentions are implemented, which utilize the visual information of images more adequately than existing MEL models do. Extensive experimental analyses are conducted to investigate the contributions of different modalities in terms of MEL, facilitating the future research on this task.

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification.

Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and translates natural source sentences in inference. The source discrepancy between training and inference hinders the translation performance of UNMT models. By carefully designing experiments, we identify two representative characteristics of the data gap in source: (1) style gap (i.e., translated vs. natural text style) that leads to poor generalization capability; (2) content gap that induces the model to produce hallucination content biased towards the target language. To narrow the data gap, we propose an online self-training approach, which simultaneously uses the pseudo parallel data {natural source, translated target} to mimic the inference scenario. Experimental results on several widely-used language pairs show that our approach outperforms two strong baselines (XLM and MASS) by remedying the style and content gaps.

Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted one-pass issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.

Supervised training of existing deep learning models for sequence labeling relies on large scale labeled datasets. Such datasets are generally created with crowd-source labeling. However, crowd-source labeling for tasks of sequence labeling can be expensive and time-consuming. Further, crowd-source labeling by external annotators may not be appropriate for data that contains user private information. Considering the above limitations of crowd-source labeling, we study interactive sequence labeling that allows training directly with the user feedback, which alleviates the annotation cost and maintains the user privacy. We identify two bias, namely, context bias and feedback bias, by formulating interactive sequence labeling via a Structural Causal Model (SCM). To alleviate the context and feedback bias based on the SCM, we identify the frequent context tokens as confounders in the backdoor adjustment and further propose an entropy-based modulation that is inspired by information theory. entities more sample-efficiently. With extensive experiments, we validate that our approach can effectively alleviate the biases and our models can be efficiently learnt with the user feedback.

We present MCPG: a simple and effectiveapproach for controllable unsupervised paraphrase generation, which is also flexible toadapt to specific domains without extra training. MCPG is controllable in different levels: local lexicons, global semantics, and universal styles. The unsupervised paradigm ofMCPG combines factual keywords and diversified semantic embeddings as local lexical andglobal semantic constraints. The semantic embeddings are diversified by standard dropout,which is exploited for the first time to increaseinference diversity by us. Moreover, MCPGis qualified with good domain adaptability byadding a transfer vector as a universal style constraint, which is refined from the exemplars retrieved from the corpus of the target domain in atraining-free way. Extensive experiments showthat MCPG outperforms state-of-the-art unsupervised baselines by a margin. Meanwhile,our domain-adapted MCPG also achieves competitive performance with strong supervisedbaselines even without training.

It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the “multi-modality problem”, including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenges to the standard cross entropy (XE) loss in NAT and is understudied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to using different loss functions for different kinds of syntactic multi-modality.

This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation task on English-Livonian.Our system is based on M2M100 with novel techniques that adapt it to the target language pair.(1) Cross-model word embedding alignment: inspired by cross-lingual word embedding alignment, we successfully transfer a pre-trained word embedding to M2M100, enabling it to support Livonian.(2) Gradual adaptation strategy: we exploit Estonian and Latvian as auxiliary languages for many-to-many translation training and then adapt to English-Livonian.(3) Data augmentation: to enlarge the parallel data for English-Livonian, we construct pseudo-parallel data with Estonian and Latvian as pivot languages.(4) Fine-tuning: to make the most of all available data, we fine-tune the model with the validation set and online back-translation, further boosting the performance. In model evaluation: (1) We find that previous work underestimated the translation performance of Livonian due to inconsistent Unicode normalization, which may cause a discrepancy of up to 14.9 BLEU score.(2) In addition to the standard validation set, we also employ round-trip BLEU to evaluate the models, which we find more appropriate for this task. Finally, our unconstrained system achieves BLEU scores of 17.0 and 30.4 for English to/from Livonian.

This paper describes AISP-SJTU’s participation in WMT 2022 shared general MT task. In this shared task, we participated in four translation directions: English-Chinese, Chinese-English, English-Japanese and Japanese-English. Our systems are based on the Transformer architecture with several novel and effective variants, including network depth and internal structure. In our experiments, we employ data filtering, large-scale back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge finetune and model ensemble. The constrained systems achieve 48.8, 29.7, 39.3 and 22.0 case-sensitive BLEU scores on EN-ZH, ZH-EN, EN-JA and JA-EN, respectively.

Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a template-to-melody module). TeleMelody has two advantages. First, it is data efficient. The template-to-melody module is trained in a self-supervised way (i.e., the source template is extracted from the target melody) that does not need any lyric-melody paired data. The lyric-to-template module is made up of some rules and a lyric-to-rhythm model, which is trained with paired lyric-rhythm data that is easier to obtain than paired lyric-melody data. Second, it is controllable. The design of the template ensures that the generated melodies can be controlled by adjusting the musical elements in the template. Both subjective and objective experimental evaluations demonstrate that TeleMelody generates melodies with higher quality, better controllability, and less requirement on paired lyric-melody data than previous generation systems.

In this paper, we introduce the task of learning unsupervised dialogue embeddings.Trivial approaches such as combining pre-trained word or sentence embeddings and encoding through pre-trained language models (PLMs) have been shown to be feasible for this task. However, these approaches typically ignore the conversational interactions between interlocutors, resulting in poor performance. To address this issue, we proposed a self-guided contrastive learning approach named dial2vec.Dial2vec considers a dialogue as an information exchange process. It captures the interaction patterns between interlocutors and leverages them to guide the learning of the embeddings corresponding to each interlocutor. Then the dialogue embedding is obtained by an aggregation of the embeddings from all interlocutors. To verify our approach, we establish a comprehensive benchmark consisting of six widely-used dialogue datasets. We consider three evaluation tasks: domain categorization, semantic relatedness, and dialogue retrieval. Dial2vec achieves on average 8.7, 9.0, and 13.8 points absolute improvements in terms of purity, Spearman’s correlation, and mean average precision (MAP) over the strongest baseline on the three tasks respectively. Further analysis shows that dial2vec obtains informative and discriminative embeddings for both interlocutors under the guidance of the conversational interactions and achieves the best performance when aggregating them through the interlocutor-level pooling strategy. All codes and data are publicly available at https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/dial2vec.

Fine-grained opinion mining (OM) has achieved increasing attraction in the natural language processing (NLP) community, which aims to find the opinion structures of “Who expressed what opinions towards what” in one sentence. In this work, motivated by its span-based representations of opinion expressions and roles, we propose a unified span-based approach for the end-to-end OM setting. Furthermore, inspired by the unified span-based formalism of OM and constituent parsing, we explore two different methods (multi-task learning and graph convolutional neural network) to integrate syntactic constituents into the proposed model to help OM. We conduct experiments on the commonly used MPQA 2.0 dataset. The experimental results show that our proposed unified span-based approach achieves significant improvements over previous works in the exact F1 score and reduces the number of wrongly-predicted opinion expressions and roles, showing the effectiveness of our method. In addition, incorporating the syntactic constituents achieves promising improvements over the strong baseline enhanced by contextualized word representations.

Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for some extremely low-resource languages such as Estonian, and UNMT systems usually perform poorly when there is not adequate training corpus for one language. In this paper, we first define and analyze the unbalanced training data scenario for UNMT. Based on this scenario, we propose UNMT self-training mechanisms to train a robust UNMT system and improve its performance in this case. Experimental results on several language pairs show that the proposed methods substantially outperform conventional UNMT systems.

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens. In this work, we propose FastCorrect 2, an error correction model that takes multiple ASR candidates as input for better correction accuracy. FastCorrect 2 adopts non-autoregressive generation for fast inference, which consists of an encoder that processes multiple source sentences and a decoder that generates the target sentence in parallel from the adjusted source sentence, where the adjustment is based on the predicted duration of each source token. However, there are some issues when handling multiple source sentences. First, it is non-trivial to leverage the voting effect from multiple source sentences since they usually vary in length. Thus, we propose a novel alignment algorithm to maximize the degree of token alignment among multiple sentences in terms of token and pronunciation similarity. Second, the decoder can only take one adjusted source sentence as input, while there are multiple source sentences. Thus, we develop a candidate predictor to detect the most suitable candidate for the decoder. Experiments on our inhouse dataset and AISHELL-1 show that FastCorrect 2 can further reduce the WER over the previous correction model with single candidate by 3.2% and 2.6%, demonstrating the effectiveness of leveraging multiple candidates in ASR error correction. FastCorrect 2 achieves better performance than the cascaded re-scoring and correction pipeline and can serve as a unified post-processing module for ASR.

Lacking sufficient human-annotated data is one main challenge for abstract meaning representation (AMR) parsing. To alleviate this problem, previous works usually make use of silver data or pre-trained language models. In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin. However, it makes the decoding relatively slower. In this work, we investigate alternative approaches to achieve competitive performance at faster speeds. We propose a simplified AMR parser and a pre-training technique for the effective usage of silver data. We conduct extensive experiments on the widely used AMR2.0 dataset and the results demonstrate that our Transformer-based AMR parser achieves the best performance among the seq2graph-based models. Furthermore, with silver data, our model achieves competitive results with the SOTA model, and the speed is an order of magnitude faster. Detailed analyses are conducted to gain more insights into our proposed model and the effectiveness of the pre-training technique.

Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results. Meanwhile, there are still several challenges for UNMT. This tutorial first introduces the background and the latest progress of UNMT. We then examine a number of challenges to UNMT and give empirical results on how well the technology currently holds up.

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-network for this task, which obtains the sentence embeddings through modeling the context-response semantic relevance by applying a feed-forward network on top of the sentence encoders. However, as the semantic textual similarity is commonly measured through the element-wise distance metrics (e.g. cosine and L2 distance), such architecture yields a large gap between training and evaluating. In this paper, we propose DialogueCSE, a dialogue-based contrastive learning approach to tackle this issue. DialogueCSE first introduces a novel matching-guided embedding (MGE) mechanism, which generates a context-aware embedding for each candidate response embedding (i.e. the context-free embedding) according to the guidance of the multi-turn context-response matching matrices. Then it pairs each context-aware embedding with its corresponding context-free embedding and finally minimizes the contrastive loss across all pairs. We evaluate our model on three multi-turn dialogue datasets: the Microsoft Dialogue Corpus, the Jing Dong Dialogue Corpus, and the E-commerce Dialogue Corpus. Evaluation results show that our approach significantly outperforms the baselines across all three datasets in terms of MAP and Spearman’s correlation measures, demonstrating its effectiveness. Further quantitative experiments show that our approach achieves better performance when leveraging more dialogue context and remains robust when less training data is provided.

Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e.,semantic entity), while the relations in-between are largely unexplored. In this paper, we adapt the popular dependency parsing model, the biaffine parser, to this entity relation extraction task. Being different from the original dependency parsing model which recognizes dependency relations between words, we identify relations between groups of words with layout information instead. We have compared different representations of the semantic entity, different VRD encoders, and different relation decoders. For the model training, we explore multi-task learning to combine entity labeling and relation extraction tasks; and for the evaluation, we conduct experiments on different datasets with filtering and augmentation. The results demonstrate that our proposed model achieves 65.96% F1 score on the FUNSD dataset. As for the real-world application, our model has been applied to the in-house customs data, achieving reliable performance in the production setting.

Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data. For Named Entity Recognition (NER), existing approaches augment the input sequence with token replacement, assuming annotations on the replaced positions unchanged. In this paper, we explore the use of paraphrasing as a more principled data augmentation scheme for NER unsupervised consistency training. Specifically, we convert Conditional Random Field (CRF) into a multi-label classification module and encourage consistency on the entity appearance between the original and paraphrased sequences. Experiments show that our method is especially effective when annotations are limited.

Opinion Role Labeling (ORL), aiming to identify the key roles of opinion, has received increasing interest. Unlike most of the previous works focusing on the English language, in this paper, we present the first work of Chinese ORL. We construct a Chinese dataset by manually translating and projecting annotations from a standard English MPQA dataset. Then, we investigate the effectiveness of cross-lingual transfer methods, including model transfer and corpus translation. We exploit multilingual BERT with Contextual Parameter Generator and Adapter methods to examine the potentials of unsupervised cross-lingual learning and our experiments and analyses for both bilingual and multilingual transfers establish a foundation for the future research of this task.

This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results. In this tutorial, we will first introduce the background and the latest progress of syntactic parsing and SRL/NMT. Then, we will summarize the key evidence about the syntactic impacts over these two concerning tasks, and explore the behind reasons from both computational and linguistic backgrounds.

In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation directions of three language pairs: English-Chinese, English-Polish on supervised machine translation track, German-Upper Sorbian on low-resource and unsupervised machine translation tracks. Based on different conditions of language pairs, we have experimented with diverse neural machine translation (NMT) techniques: document-enhanced NMT, XLM pre-trained language model enhanced NMT, bidirectional translation as a pre-training, reference language based UNMT, data-dependent gaussian prior objective, and BT-BLEU collaborative filtering self-training. We also used the TF-IDF algorithm to filter the training set to obtain a domain more similar set with the test set for finetuning. In our submissions, the primary systems won the first place on English to Chinese, Polish to English, and German to Upper Sorbian translation directions.

Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-identified predicates, previous work has focused on the relationships between predicates and arguments and the correlations between arguments at most, while the correlations between predicates have been neglected for a long time. High-order features and structure learning were very common in modeling such correlations before the neural network era. In this paper, we introduce a high-order graph structure for the neural semantic role labeling model, which enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models and further boost our baseline to achieve new state-of-the-art results.

Chinese spelling check is a challenging task due to the characteristics of the Chinese language, such as the large character set, no word boundary, and short word length. On the one hand, most of the previous works only consider corrections with similar character pronunciation or shape, failing to correct visually and phonologically irrelevant typos. On the other hand, pipeline-style architectures are widely adopted to deal with different types of spelling errors in individual modules, which is difficult to optimize. In order to handle these issues, in this work, 1) we extend the traditional confusion sets with semantical candidates to cover different types of errors; 2) we propose a chunk-based framework to correct single-character and multi-character word errors uniformly; and 3) we adopt a global optimization strategy to enable a sentence-level correction selection. The experimental results show that the proposed approach achieves a new state-of-the-art performance on three benchmark datasets, as well as an optical character recognition dataset.

Pretrained Language Models (PLMs) have improved the performance of natural language understanding in recent years. Such models are pretrained on large corpora, which encode the general prior knowledge of natural languages but are agnostic to information characteristic of downstream tasks. This often results in overfitting when fine-tuned with low resource datasets where task-specific information is limited. In this paper, we integrate label information as a task-specific prior into the self-attention component of pretrained BERT models. Experiments on several benchmarks and real-word datasets suggest that the proposed approach can largely improve the performance of pretrained models when fine-tuning with small datasets.

Exploiting a common language as an auxiliary for better translation has a long tradition in machine translation and lets supervised learning-based machine translation enjoy the enhancement delivered by the well-used pivot language in the absence of a source language to target language parallel corpus. The rise of unsupervised neural machine translation (UNMT) almost completely relieves the parallel corpus curse, though UNMT is still subject to unsatisfactory performance due to the vagueness of the clues available for its core back-translation training. Further enriching the idea of pivot translation by extending the use of parallel corpora beyond the source-target paradigm, we propose a new reference language-based framework for UNMT, RUNMT, in which the reference language only shares a parallel corpus with the source, but this corpus still indicates a signal clear enough to help the reconstruction training of UNMT through a proposed reference agreement mechanism. Experimental results show that our methods improve the quality of UNMT over that of a strong baseline that uses only one auxiliary language, demonstrating the usefulness of the proposed reference language-based UNMT and establishing a good start for the community.

Recent years have witnessed a surge of interests of using neural topic models for automatic topic extraction from text, since they avoid the complicated mathematical derivations for model inference as in traditional topic models such as Latent Dirichlet Allocation (LDA). However, these models either typically assume improper prior (e.g. Gaussian or Logistic Normal) over latent topic space or could not infer topic distribution for a given document. To address these limitations, we propose a neural topic modeling approach, called Bidirectional Adversarial Topic (BAT) model, which represents the first attempt of applying bidirectional adversarial training for neural topic modeling. The proposed BAT builds a two-way projection between the document-topic distribution and the document-word distribution. It uses a generator to capture the semantic patterns from texts and an encoder for topic inference. Furthermore, to incorporate word relatedness information, the Bidirectional Adversarial Topic model with Gaussian (Gaussian-BAT) is extended from BAT. To verify the effectiveness of BAT and Gaussian-BAT, three benchmark corpora are used in our experiments. The experimental results show that BAT and Gaussian-BAT obtain more coherent topics, outperforming several competitive baselines. Moreover, when performing text clustering based on the extracted topics, our models outperform all the baselines, with more significant improvements achieved by Gaussian-BAT where an increase of near 6% is observed in accuracy.

Neural machine translation (NMT) encodes the source sentence in a universal way to generate the target sentence word-by-word. However, NMT does not consider the importance of word in the sentence meaning, for example, some words (i.e., content words) express more important meaning than others (i.e., function words). To address this limitation, we first utilize word frequency information to distinguish between content and function words in a sentence, and then design a content word-aware NMT to improve translation performance. Empirical results on the WMT14 English-to-German, WMT14 English-to-French, and WMT17 Chinese-to-English translation tasks show that the proposed methods can significantly improve the performance of Transformer-based NMT.

Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews. Most recent efforts adopt attention-based neural network models to implicitly connect aspects with opinion words. However, due to the complexity of language and the existence of multiple aspects in a single sentence, these models often confuse the connections. In this paper, we address this problem by means of effective encoding of syntax information. Firstly, we define a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree. Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction. Extensive experiments are conducted on the SemEval 2014 and Twitter datasets, and the experimental results confirm that the connections between aspects and opinion words can be better established with our approach, and the performance of the graph attention network (GAT) is significantly improved as a consequence.

Opinion role labeling (ORL) is a fine-grained opinion analysis task and aims to answer “who expressed what kind of sentiment towards what?”. Due to the scarcity of labeled data, ORL remains challenging for data-driven methods. In this work, we try to enhance neural ORL models with syntactic knowledge by comparing and integrating different representations. We also propose dependency graph convolutional networks (DEPGCN) to encode parser information at different processing levels. In order to compensate for parser inaccuracy and reduce error propagation, we introduce multi-task learning (MTL) to train the parser and the ORL model simultaneously. We verify our methods on the benchmark MPQA corpus. The experimental results show that syntactic information is highly valuable for ORL, and our final MTL model effectively boosts the F1 score by 9.29 over the syntax-agnostic baseline. In addition, we find that the contributions from syntactic knowledge do not fully overlap with contextualized word representations (BERT). Our best model achieves 4.34 higher F1 score than the current state-ofthe-art.

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. That is, research on multilingual UNMT has been limited. In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. On the basis of the empirical findings, we propose two knowledge distillation methods to further enhance multilingual UNMT performance. Our experiments on a dataset with English translated to and from twelve other languages (including three language families and six language branches) show remarkable results, surpassing strong unsupervised individual baselines while achieving promising performance between non-English language pairs in zero-shot translation scenarios and alleviating poor performance in low-resource language pairs.

Generating fluent and informative responses is of critical importance for task-oriented dialogue systems. Existing pipeline approaches generally predict multiple dialogue acts first and use them to assist response generation. There are at least two shortcomings with such approaches. First, the inherent structures of multi-domain dialogue acts are neglected. Second, the semantic associations between acts and responses are not taken into account for response generation. To address these issues, we propose a neural co-generation model that generates dialogue acts and responses concurrently. Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed. We train the two modules jointly using an uncertainty loss to adjust their task weights adaptively. Extensive experiments are conducted on the large-scale MultiWOZ dataset and the results show that our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.

Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation (NMT). However, it is challenging to extend them into the advanced Transformer architecture, which is more complicated than RNN. This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer. In addition, to further reduce the bias problem in the gate mechanism, this paper proposes a regularization method to guide the learning of the gates with supervision automatically generated using pointwise mutual information. Extensive experiments on 4 translation datasets demonstrate that the proposed model obtains an averaged gain of 1.0 BLEU score over a strong Transformer baseline.

Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, achieving state-of-the-art performance. However, due to the variety of users’ emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain. In this paper, we pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets, and utilize it for cross-domain sentiment analysis task without fine-tuning. We propose several pre-training tasks based on existing lexicons and annotations at both token and sentence levels, such as emoticons, sentiment words, and ratings, without human interference. A series of experiments are conducted and the results indicate the great advantages of our model. We obtain new state-of-the-art results in all the cross-domain sentiment analysis tasks, and our proposed SentiX can be trained with only 1% samples (18 samples) and it achieves better performance than BERT with 90% samples.

Recently, due to the interplay between syntax and semantics, incorporating syntactic knowledge into neural semantic role labeling (SRL) has achieved much attention. Most of the previous syntax-aware SRL works focus on explicitly modeling homogeneous syntactic knowledge over tree outputs. In this work, we propose to encode heterogeneous syntactic knowledge for SRL from both explicit and implicit representations. First, we introduce graph convolutional networks to explicitly encode multiple heterogeneous dependency parse trees. Second, we extract the implicit syntactic representations from syntactic parser trained with heterogeneous treebanks. Finally, we inject the two types of heterogeneous syntax-aware representations into the base SRL model as extra inputs. We conduct experiments on two widely-used benchmark datasets, i.e., Chinese Proposition Bank 1.0 and English CoNLL-2005 dataset. Experimental results show that incorporating heterogeneous syntactic knowledge brings significant improvements over strong baselines. We further conduct detailed analysis to gain insights on the usefulness of heterogeneous (vs. homogeneous) syntactic knowledge and the effectiveness of our proposed approaches for modeling such knowledge.

Unsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training text sentences while with only a slightly worse performance than supervised neural machine translation which requires expensive annotated translation pairs on some translation tasks. In most studies, the UMNT is trained with clean data without considering its robustness to the noisy data. However, in real-world scenarios, there usually exists noise in the collected input sentences which degrades the performance of the translation system since the UNMT is sensitive to the small perturbations of the input sentences. In this paper, we first time explicitly take the noisy data into consideration to improve the robustness of the UNMT based systems. First of all, we clearly defined two types of noises in training sentences, i.e., word noise and word order noise, and empirically investigate its effect in the UNMT, then we propose adversarial training methods with denoising process in the UNMT. Experimental results on several language pairs show that our proposed methods substantially improved the robustness of the conventional UNMT systems in noisy scenarios.

This paper describes our participating system on the Chinese Grammatical Error Diagnosis (CGED) 2020 shared task. For the detection subtask, we propose two BERT-based approaches 1) with syntactic dependency trees enhancing the model performance and 2) under the multi-task learning framework to combine the sequence labeling and the sequence-to-sequence (seq2seq) models. For the correction subtask, we utilize the masked language model, the seq2seq model and the spelling check model to generate corrections based on the detection results. Finally, our system achieves the highest recall rate on the top-3 correction and the second best F1 score on identification level and position level.

Graph Neural Networks (GNNs) that capture the relationships between graph nodes via message passing have been a hot research direction in the natural language processing community. In this paper, we propose Graph Topic Model (GTM), a GNN based neural topic model that represents a corpus as a document relationship graph. Documents and words in the corpus become nodes in the graph and are connected based on document-word co-occurrences. By introducing the graph structure, the relationships between documents are established through their shared words and thus the topical representation of a document is enriched by aggregating information from its neighboring nodes using graph convolution. Extensive experiments on three datasets were conducted and the results demonstrate the effectiveness of the proposed approach.

Advances on deep generative models have attracted significant research interest in neural topic modeling. The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs Dirichlet prior to capture the semantic patterns in latent topics. It is effective in discovering coherent topics but unable to infer topic distributions for given documents or utilize available document labels. To overcome such limitations, we propose Topic Modeling with Cycle-consistent Adversarial Training (ToMCAT) and its supervised version sToMCAT. ToMCAT employs a generator network to interpret topics and an encoder network to infer document topics. Adversarial training and cycle-consistent constraints are used to encourage the generator and the encoder to produce realistic samples that coordinate with each other. sToMCAT extends ToMCAT by incorporating document labels into the topic modeling process to help discover more coherent topics. The effectiveness of the proposed models is evaluated on unsupervised/supervised topic modeling and text classification. The experimental results show that our models can produce both coherent and informative topics, outperforming a number of competitive baselines.

This paper describes our SJTU-NICT’s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Our system uses a graph-based approach to model a variety of semantic graph parsing tasks. Our main contributions in the submitted system are summarized as follows: 1. Our model is fully end-to-end and is capable of being trained only on the given training set which does not rely on any other extra training source including the companion data provided by the organizer; 2. We extend our graph pruning algorithm to a variety of semantic graphs, solving the problem of excessive semantic graph search space; 3. We introduce multi-task learning for multiple objectives within the same framework. The evaluation results show that our system achieved second place in the overall F₁ score and achieved the best F₁ score on the DM framework.

In this paper, we describe our participating systems in the shared task on Cross- Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). The task includes five frameworks for graph-based meaning representations, i.e., DM, PSD, EDS, UCCA, and AMR. One common characteristic of our systems is that we employ graph-based methods instead of transition-based methods when predicting edges between nodes. For SDP, we jointly perform edge prediction, frame tagging, and POS tagging via multi-task learning (MTL). For UCCA, we also jointly model a constituent tree parsing and a remote edge recovery task. For both EDS and AMR, we produce nodes first and edges second in a pipeline fashion. External resources like BERT are found helpful for all frameworks except AMR. Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.

In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions. We focused on leveraging multilingual transfer learning and back-translation for the extremely low-resource language pairs: Kazakh↔English and Gujarati↔English translation. For the Chinese↔English translation, we used the provided parallel data augmented with a large quantity of back-translated monolingual data to train state-of-the-art NMT systems. We then employed techniques that have been proven to be most effective, such as back-translation, fine-tuning, and model ensembling, to generate the primary submissions of Chinese↔English. For English→Finnish, our submission from WMT18 remains a strong baseline despite the increase in parallel corpora for this year’s task.

This paper presents the NICT’s participation in the WMT19 unsupervised news translation task. We participated in the unsupervised translation direction: German-Czech. Our primary submission to the task is the result of a simple combination of our unsupervised neural and statistical machine translation systems. Our system is ranked first for the German-to-Czech translation task, using only the data provided by the organizers (“constraint’”), according to both BLEU-cased and human evaluation. We also performed contrastive experiments with other language pairs, namely, English-Gujarati and English-Kazakh, to better assess the effectiveness of unsupervised machine translation in for distant language pairs and in truly low-resource conditions.

To extract the structured representations of open-domain events, Bayesian graphical models have made some progress. However, these approaches typically assume that all words in a document are generated from a single event. While this may be true for short text such as tweets, such an assumption does not generally hold for long text such as news articles. Moreover, Bayesian graphical models often rely on Gibbs sampling for parameter inference which may take long time to converge. To address these limitations, we propose an event extraction model based on Generative Adversarial Nets, called Adversarial-neural Event Model (AEM). AEM models an event with a Dirichlet prior and uses a generator network to capture the patterns underlying latent events. A discriminator is used to distinguish documents reconstructed from the latent events and the original documents. A byproduct of the discriminator is that the features generated by the learned discriminator network allow the visualization of the extracted events. Our model has been evaluated on two Twitter datasets and a news article dataset. Experimental results show that our model outperforms the baseline approaches on all the datasets, with more significant improvements observed on the news article dataset where an increase of 15% is observed in F-measure.

As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence. This paper investigates how to incorporate syntactic knowledge into the SRL task effectively. We present different approaches of en- coding the syntactic information derived from dependency trees of different quality and representations; we propose a syntax-enhanced self-attention model and compare it with other two strong baseline methods; and we con- duct experiments with newly published deep contextualized word representations as well. The experiment results demonstrate that with proper incorporation of the high quality syntactic information, our model achieves a new state-of-the-art performance for the Chinese SRL task on the CoNLL-2009 dataset.

Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models. To obtain a powerful attention helping with reproducing the most salient information and avoiding repetitions, we augment the vanilla attention model from both local and global aspects. We propose attention refinement unit paired with local variance loss to impose supervision on the attention model at each decoding step, and we also propose a global variance loss to optimize the attention distributions of all decoding steps from the global perspective. The performances on CNN/Daily Mail dataset verify the effectiveness of our methods.

In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT’14 English-to-German and NIST Chinese-to-English translation tasks.

This paper presents the NICT’s participation (team ID: NICT) in the 6th Workshop on Asian Translation (WAT-2019) shared translation task, specifically Myanmar (Burmese) - English task in both translation directions. We built neural machine translation (NMT) systems for these tasks. Our NMT systems were trained with language model pretraining. Back-translation technology is adopted to NMT. Our NMT systems rank the third in English-to-Myanmar and the second in Myanmar-to-English according to BLEU score.

Unsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several language pairs. In previous methods, UBWE is first trained using non-parallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT. That is, the training of UBWE and UNMT are separate. In this paper, we first empirically investigate the relationship between UBWE and UNMT. The empirical findings show that the performance of UNMT is significantly affected by the performance of UBWE. Thus, we propose two methods that train UNMT with UBWE agreement. Empirical results on several language pairs show that the proposed methods significantly outperform conventional UNMT.

The reordering model plays an important role in phrase-based statistical machine translation. However, there are few works that exploit the reordering information in neural machine translation. In this paper, we propose a reordering mechanism to learn the reordering embedding of a word based on its contextual information. These learned reordering embeddings are stacked together with self-attention networks to learn sentence representation for machine translation. The reordering mechanism can be easily integrated into both the encoder and the decoder in the Transformer translation system. Experimental results on WMT’14 English-to-German, NIST Chinese-to-English, and WAT Japanese-to-English translation tasks demonstrate that the proposed methods can significantly improve the performance of the Transformer.

The success of neural summarization models stems from the meticulous encodings of source articles. To overcome the impediments of limited and sometimes noisy training data, one promising direction is to make better use of the available training data by applying filters during summarization. In this paper, we propose a novel Bi-directional Selective Encoding with Template (BiSET) model, which leverages template discovered from training data to softly select key information from each source article to guide its summarization process. Extensive experiments on a standard summarization dataset are conducted and the results show that the template-equipped BiSET model manages to improve the summarization performance significantly with a new state of the art.

During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data. However, unsupervised approaches make limited progress so far due to the intrinsic difficulty of both domain adaptation and parsing. This paper tackles the semi-supervised domain adaptation problem for Chinese dependency parsing, based on two newly-annotated large-scale domain-aware datasets. We propose a simple domain embedding approach to merge the source- and target-domain training data, which is shown to be more effective than both direct corpus concatenation and multi-task learning. In order to utilize unlabeled target-domain data, we employ the recent contextualized word representations and show that a simple fine-tuning procedure can further boost cross-domain parsing accuracy by large margin.

The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance.

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes. We hypothesize that the diversity in segmentations may affect the NMT performance. To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training. We propose two methods: 1) lattice positional encoding and 2) lattice-aware self-attention. These two methods can be used together and show complementary to each other to further improve translation performance. Experiment results show superiorities of lattice-based encoders in word-level and subword-level representations over conventional Transformer encoder.

This paper presents the NICT’s participation to the WMT18 shared news translation task. We participated in the eight translation directions of four language pairs: Estonian-English, Finnish-English, Turkish-English and Chinese-English. For each translation direction, we prepared state-of-the-art statistical (SMT) and neural (NMT) machine translation systems. Our NMT systems were trained with the transformer architecture using the provided parallel data enlarged with a large quantity of back-translated monolingual data that we generated with a new incremental training framework. Our primary submissions to the task are the result of a simple combination of our SMT and NMT systems. Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.

This paper presents the NICT’s participation in the WMT18 shared parallel corpus filtering task. The organizers provided 1 billion words German-English corpus crawled from the web as part of the Paracrawl project. This corpus is too noisy to build an acceptable neural machine translation (NMT) system. Using the clean data of the WMT18 shared news translation task, we designed several features and trained a classifier to score each sentence pairs in the noisy data. Finally, we sampled 100 million and 10 million words and built corresponding NMT systems. Empirical results show that our NMT systems trained on sampled data achieve promising performance.

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently no matter how similar they are. However, this might be inefficient since some partial hypotheses can contain only local differences that will not influence future predictions. In this work, we introduce recombination in NMT decoding based on the concept of the “equivalence” of partial hypotheses. Heuristically, we use a simple n-gram suffix based equivalence function and adapt it into beam search decoding. Through experiments on large-scale Chinese-to-English and English-to-Germen translation tasks, we show that the proposed method can obtain similar translation quality with a smaller beam size, making NMT decoding more efficient.

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured difference between the training costs of two iterations. Further, in each epoch, a certain percentage of sentences are dynamically sampled according to their weights. Empirical results based on the NIST Chinese-to-English and the WMT English-to-German tasks show that the proposed method can significantly accelerate the NMT training and improve the NMT performance.

Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points.

Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel NMT with source dependency representation to improve translation performance of NMT, especially long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system.

Although new corpora are becoming increasingly available for machine translation, only those that belong to the same or similar domains are typically able to improve translation performance. Recently Neural Machine Translation (NMT) has become prominent in the field. However, most of the existing domain adaptation methods only focus on phrase-based machine translation. In this paper, we exploit the NMT’s internal embedding of the source sentence and use the sentence embedding similarity to select the sentences which are close to in-domain data. The empirical adaptation results on the IWSLT English-French and NIST Chinese-English tasks show that the proposed methods can substantially improve NMT performance by 2.4-9.0 BLEU points, outperforming the existing state-of-the-art baseline by 2.3-4.5 BLEU points.

In Neural Machine Translation (NMT), each word is represented as a low-dimension, real-value vector for encoding its syntax and semantic information. This means that even if the word is in a different sentence context, it is represented as the fixed vector to learn source representation. Moreover, a large number of Out-Of-Vocabulary (OOV) words, which have different syntax and semantic information, are represented as the same vector representation of “unk”. To alleviate this problem, we propose a novel context-aware smoothing method to dynamically learn a sentence-specific vector for each word (including OOV words) depending on its local context words in a sentence. The learned context-aware representation is integrated into the NMT to improve the translation performance. Empirical results on NIST Chinese-to-English translation task show that the proposed approach achieves 1.78 BLEU improvements on average over a strong attentional NMT, and outperforms some existing systems.

Although more additional corpora are now available for Statistical Machine Translation (SMT), only the ones which belong to the same or similar domains of the original corpus can indeed enhance SMT performance directly. A series of SMT adaptation methods have been proposed to select these similar-domain data, and most of them focus on sentence selection. In comparison, phrase is a smaller and more fine grained unit for data selection, therefore we propose a straightforward and efficient connecting phrase based adaptation method, which is applied to both bilingual phrase pair and monolingual n-gram adaptation. The proposed method is evaluated on IWSLT/NIST data sets, and the results show that phrase based SMT performances are significantly improved (up to +1.6 in comparison with phrase based SMT baseline system and +0.9 in comparison with existing methods).

Extracting instances of sentiment-oriented relations from user-generated web documents is important for online marketing analysis. Unlike previous work, we formulate this extraction task as a structured prediction problem and design the corresponding inference as an integer linear program. Our latent structural SVM based model can learn from training corpora that do not contain explicit annotations of sentiment-bearing expressions, and it can simultaneously recognize instances of both binary (polarity) and ternary (comparative) relations with regard to entity mentions of interest. The empirical evaluation shows that our approach significantly outperforms state-of-the-art systems across domains (cameras and movies) and across genres (reviews and forum posts). The gold standard corpus that we built will also be a valuable resource for the community.

Paraphrases and paraphrasing algorithms have been found of great importance in various natural language processing tasks. While most paraphrase extraction approaches extract equivalent sentences, sentences are an inconvenient unit for further processing, because they are too specific, and often not exact paraphrases. Paraphrase fragment extraction is a technique that post-processes sentential paraphrases and prunes them to more convenient phrase-level units. We present a new approach that uses semantic roles to extract paraphrase fragments from sentence pairs that share semantic content to varying degrees, including full paraphrases. In contrast to previous systems, the use of semantic parses allows for extracting paraphrases with high wording variance and different syntactic categories. The approach is tested on four different input corpora and compared to two previous systems for extracting paraphrase fragments. Our system finds three times as many good paraphrase fragments per sentence pair as the baselines, and at the same time outputs 30% fewer unrelated fragment pairs.

We present the ongoing development of MCG, a linguistically deep and precise grammar for Mandarin Chinese together with its accompanying treebank, both based on the linguistic framework of HPSG, and using MRS as the semantic representation. We highlight some key features of our grammar design, and review a number of challenging phenomena, with comparisons to alternative linguistic treatments and implementations. One of the distinguishing characteristics of our approach is the tight integration of grammar and treebank development. The two-step treebank annotation procedure benefits from the efficiency of the discriminant-based annotation approach, while giving the annotators full freedom of producing extra-grammatical structures. This not only allows the creation of a precise and full-coverage treebank with an imperfect grammar, but also provides prompt feedback for grammarians to identify the errors in the grammar design and implementation. Preliminary evaluation and error analysis shows that the grammar already covers most of the core phenomena for Mandarin Chinese, and the treebank annotation procedure reaches a stable speed of 35 sentences per hour with satisfying quality.

Finding useful questions is a challenging task in Community Question Answering (CQA). There are two key issues need to be resolved: 1) what is a useful question to the given reference question; and furthermore 2) what kind of relations exist between a given pair of questions. In order to answer these two questions, in this paper, we propose a fine-grained inventory of textual semantic relations between questions and annotate a corpus constructed from the WikiAnswers website. We also extract large archives of question pairs with user-generated links and use them as labeled data for separating useful questions from neutral ones, achieving 72.2% of accuracy. We find such online CQA repositories valuable resources for related research.

In this paper, we present our work on constructing a textual semantic relation corpus by making use of an existing treebank annotated with discourse relations. We extract adjacent text span pairs and group them into six categories according to the different discourse relations between them. After that, we present the details of our annotation scheme, which includes six textual semantic relations, 'backward entailment', 'forward entailment', 'equality', 'contradiction', 'overlapping', and 'independent'. We also discuss some ambiguous examples to show the difficulty of such annotation task, which cannot be easily done by an automatic mapping between discourse relations and semantic relations. We have two annotators and each of them performs the task twice. The basic statistics on the constructed corpus looks promising: we achieve 81.17% of agreement on the six semantic relation annotation with a .718 kappa score, and it increases to 91.21% if we collapse the last two labels with a .775 kappa score.

In this paper, we describe our hybrid parsing model on the Mandarin Chinese processing. In particular, we work on the Tsinghua Chinese Treebank (TCT), whose annotation has both constitutes and the head information of each constitute. The model we design combines the mainstream constitute parsing and dependency parsing. We present in detail 1) how to (partially) encode the head information into the constitute parsing, 2) how to encode constitute information into the dependency parsing, and 3) how to restore the head information using the dependency structure. For each of them, we take different strategies to deal with different cases. In an open shared task evaluation, we achieve an f1-score of 85.23% for the constitute parsing, 82.35% with partial head information, and 74.27% with complete head information. The error analysis shows the challenge of restoring multiple-headed constitutes and also some potentials to use the dependency structure to guide the constitute parsing, which will be our future work to explore.