Zhongyuan Wang


2022

pdf bib
RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval
Xing Wu | Chaochen Gao | Zijia Lin | Zhongyuan Wang | Jizhong Han | Songlin Hu
Findings of the Association for Computational Linguistics: EMNLP 2022

Video language pre-training methods have mainly adopted sparse sampling techniques to alleviate the temporal redundancy of videos. Though effective, sparse sampling still suffers inter-modal redundancy: visual redundancy and textual redundancy. Compared with highly generalized text, sparsely sampled frames usually contain text-independent portions, called visual redundancy. Sparse sampling is also likely to miss important frames corresponding to some text portions, resulting in textual redundancy. Inter-modal redundancy leads to a mismatch of video and text information, hindering the model from better learning the shared semantics across modalities. To alleviate it, we propose Redundancy-aware Video-language Pre-training. We design a redundancy measurement of video patches and text tokens by calculating the cross-modal minimum dis-similarity. Then, we penalize the high-redundant video patches and text tokens through a proposed redundancy-aware contrastive learning. We evaluate our method on four benchmark datasets, MSRVTT, MSVD, DiDeMo, and LSMDC, achieving a significant improvement over the previous state-of-the-art results.

pdf bib
InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings
Xing Wu | Chaochen Gao | Zijia Lin | Jizhong Han | Zhongyuan Wang | Songlin Hu
Findings of the Association for Computational Linguistics: EMNLP 2022

Contrastive learning has been extensively studied in sentence embedding learning, which assumes that the embeddings of different views of the same sentence are closer. The constraint brought by this assumption is weak, and a good sentence representation should also be able to reconstruct the original sentence fragments. Therefore, this paper proposes an information-aggregated contrastive learning framework for learning unsupervised sentence embeddings, termed InfoCSE.InfoCSE forces the representation of [CLS] positions to aggregate denser sentence information by introducing an additional Masked language model task and a well-designed network. We evaluate the proposed InfoCSE on several benchmark datasets w.r.t the semantic text similarity (STS) task. Experimental results show that InfoCSE outperforms SimCSE by an average Spearman correlation of 2.60% on BERT-base, and 1.77% on BERT-large, achieving state-of-the-art results among unsupervised sentence representation learning methods.

pdf bib
ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding
Xing Wu | Chaochen Gao | Liangjun Zang | Jizhong Han | Zhongyuan Wang | Songlin Hu
Proceedings of the 29th International Conference on Computational Linguistics

Contrastive learning has been attracting much attention for learning unsupervised sentence embeddings. The current state-of-the-art unsupervised method is the unsupervised SimCSE (unsup-SimCSE). Unsup-SimCSE takes dropout as a minimal data augmentation method, and passes the same input sentence to a pre-trained Transformer encoder (with dropout turned on) twice to obtain the two corresponding embeddings to build a positive pair. As the length information of a sentence will generally be encoded into the sentence embeddings due to the usage of position embedding in Transformer, each positive pair in unsup-SimCSE actually contains the same length information. And thus unsup-SimCSE trained with these positive pairs is probably biased, which would tend to consider that sentences of the same or similar length are more similar in semantics. Through statistical observations, we find that unsup-SimCSE does have such a problem. To alleviate it, we apply a simple repetition operation to modify the input sentence, and then pass the input sentence and its modified counterpart to the pre-trained Transformer encoder, respectively, to get the positive pair. Additionally, we draw inspiration from the community of computer vision and introduce a momentum contrast, enlarging the number of negative pairs without additional calculations. The proposed two modifications are applied on positive and negative pairs separately, and build a new sentence embedding method, termed Enhanced Unsup-SimCSE (ESimCSE). We evaluate the proposed ESimCSE on several benchmark datasets w.r.t the semantic text similarity (STS) task. Experimental results show that ESimCSE outperforms the state-of-the-art unsup-SimCSE by an average Spearman correlation of 2.02% on BERT-base.

pdf bib
Smoothed Contrastive Learning for Unsupervised Sentence Embedding
Xing Wu | Chaochen Gao | Yipeng Su | Jizhong Han | Zhongyuan Wang | Songlin Hu
Proceedings of the 29th International Conference on Computational Linguistics

Unsupervised contrastive sentence embedding models, e.g., unsupervised SimCSE, use the InfoNCE loss function in training. Theoretically, we expect to use larger batches to get more adequate comparisons among samples and avoid overfitting. However, increasing batch size leads to performance degradation when it exceeds a threshold, which is probably due to the introduction of false-negative pairs through statistical observation. To alleviate this problem, we introduce a simple smoothing strategy upon the InfoNCE loss function, termed Gaussian Smoothed InfoNCE (GS-InfoNCE). In other words, we add random Gaussian noise as an extension to the negative pairs without increasing the batch size. Through experiments on the semantic text similarity tasks, though simple, the proposed smoothing strategy brings improvements to unsupervised SimCSE.

pdf bib
Adaptive Unsupervised Self-training for Disfluency Detection
Zhongyuan Wang | Yixuan Wang | Shaolei Wang | Wanxiang Che
Proceedings of the 29th International Conference on Computational Linguistics

Supervised methods have achieved remarkable results in disfluency detection. However, in real-world scenarios, human-annotated data is difficult to obtain. Recent works try to handle disfluency detection with unsupervised self-training, which can exploit existing large-scale unlabeled data efficiently. However, their self-training-based methods suffer from the problems of selection bias and error accumulation. To tackle these problems, we propose an adaptive unsupervised self-training method for disfluency detection. Specifically, we re-weight the importance of each training example according to its grammatical feature and prediction confidence. Experiments on the Switchboard dataset show that our method improves 2.3 points over the current SOTA unsupervised method. Moreover, our method is competitive with the SOTA supervised method.

2020

pdf bib
Table Fact Verification with Structure-Aware Transformer
Hongzhi Zhang | Yingyao Wang | Sirui Wang | Xuezhi Cao | Fuzheng Zhang | Zhongyuan Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Verifying fact on semi-structured evidence like tables requires the ability to encode structural information and perform symbolic reasoning. Pre-trained language models trained on natural language could not be directly applied to encode tables, because simply linearizing tables into sequences will lose the cell alignment information. To better utilize pre-trained transformers for table representation, we propose a Structure-Aware Transformer (SAT), which injects the table structural information into the mask of the self-attention layer. A method to combine symbolic and linguistic reasoning is also explored for this task. Our method outperforms baseline with 4.93% on TabFact, a large scale table verification dataset.

pdf bib
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection
Shaolei Wang | Zhongyuan Wang | Wanxiang Che | Ting Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice. There have been several proposals to alleviate this issue with, for instance, self-supervised learning techniques, but they still require human-annotated corpora. In this work, we explore the unsupervised learning paradigm which can potentially work with unlabeled text corpora that are cheaper and easier to obtain. Our model builds upon the recent work on Noisy Student Training, a semi-supervised learning approach that extends the idea of self-training. Experimental results on the commonly used English Switchboard test set show that our approach achieves competitive performance compared to the previous state-of-the-art supervised systems using contextualized word embeddings (e.g. BERT and ELECTRA).

pdf bib
Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis
Shaolei Wang | Baoxin Wang | Jiefu Gong | Zhongyuan Wang | Xiao Hu | Xingyi Duan | Zizhuo Shen | Gang Yue | Ruiji Fu | Dayong Wu | Wanxiang Che | Shijin Wang | Guoping Hu | Ting Liu
Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications

Grammatical error diagnosis is an important task in natural language processing. This paper introduces our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) and disordered words (W). Our system is built on the model of multi-layer bidirectional transformer encoder and ResNet is integrated into the encoder to improve the performance. We also explore two ensemble strategies including weighted averaging and stepwise ensemble selection from libraries of models to improve the performance of single model. In official evaluation, our system obtains the highest F1 scores at identification level and position level. We also recommend error corrections for specific error types and achieve the second highest F1 score at correction level.

pdf bib
Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension
Xuemiao Zhang | Kun Zhou | Sirui Wang | Fuzheng Zhang | Zhongyuan Wang | Junfei Liu
Proceedings of the 28th International Conference on Computational Linguistics

Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise. Existing related methods usually incorporate extra submodels to help filter noise before the noisy data is input to main models. However, these multistage methods often make training difficult, and the qualities of submodels are hard to be controlled. In this paper, we first explore and analyze the essential characteristics of noise from the perspective of loss distribution, and find that in the early stage of training, noisy samples usually lead to significantly larger loss values than clean ones. Based on the observation, we propose a hierarchical loss correction strategy to avoid fitting noise and enhance clean supervision signals, including using an unsupervisedly fitted Gaussian mixture model to calculate the weight factors for all losses to correct the loss distribution, and employ a hard bootstrapping loss to modify loss function. Experimental results on different weakly supervised MRC datasets show that the proposed methods can help improve models significantly.

pdf bib
Syntactic Graph Convolutional Network for Spoken Language Understanding
Keqing He | Shuyu Lei | Yushu Yang | Huixing Jiang | Zhongyuan Wang
Proceedings of the 28th International Conference on Computational Linguistics

Slot filling and intent detection are two major tasks for spoken language understanding. In most existing work, these two tasks are built as joint models with multi-task learning with no consideration of prior linguistic knowledge. In this paper, we propose a novel joint model that applies a graph convolutional network over dependency trees to integrate the syntactic structure for learning slot filling and intent detection jointly. Experimental results show that our proposed model achieves state-of-the-art performance on two public benchmark datasets and outperforms existing work. At last, we apply the BERT model to further improve the performance on both slot filling and intent detection.

2016

bib
Understanding Short Texts
Zhongyuan Wang | Haixun Wang
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

Billions of short texts are produced every day, in the form of search queries, ad keywords, tags, tweets, messenger conversations, social network posts, etc. Unlike documents, short texts have some unique characteristics which make them difficult to handle. First, short texts, especially search queries, do not always observe the syntax of a written language. This means traditional NLP techniques, such as syntactic parsing, do not always apply to short texts. Second, short texts contain limited context. The majority of search queries contain less than 5 words, and tweets can have no more than 140 characters. Because of the above reasons, short texts give rise to a significant amount of ambiguity, which makes them extremely difficult to handle. On the other hand, many applications, including search engines, ads, automatic question answering, online advertising, recommendation systems, etc., rely on short text understanding. In all these applications, the necessary first step is to transform an input text into a machine-interpretable representation, namely to "understand" the short text. A growing number of approaches leverage external knowledge to address the issue of inadequate contextual information that accompanies the short texts. These approaches can be classified into two categories: Explicit Representation Model (ERM) and Implicit Representation Model (IRM). In this tutorial, we will present a comprehensive overview of short text understanding based on explicit semantics (knowledge graph representation, acquisition, and reasoning) and implicit semantics (embedding and deep learning). Specifically, we will go over various techniques in knowledge acquisition, representation, and inferencing has been proposed for text understanding, and we will describe massive structured and semi-structured data that have been made available in the recent decade that directly or indirectly encode human knowledge, turning the knowledge representation problems into a computational grand challenge with feasible solutions insight.

pdf bib
Syntactic Parsing of Web Queries
Xiangyan Sun | Haixun Wang | Yanghua Xiao | Zhongyuan Wang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Probabilistic Prototype Model for Serendipitous Property Mining
Taesung Lee | Seung-won Hwang | Zhongyuan Wang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Besides providing the relevant information, amusing users has been an important role of the web. Many web sites provide serendipitous (unexpected but relevant) information to draw user traffic. In this paper, we study the representative scenario of mining an amusing quiz. An existing approach leverages a knowledge base to mine an unexpected property then find quiz questions on such property, based on prototype theory in cognitive science. However, existing deterministic model is vulnerable to noise in the knowledge base. Therefore, we instead propose to leverage probabilistic approach to build a prototype that can overcome noise. Our extensive empirical study shows that our approach not only significantly outperforms baselines by 0.06 in accuracy, and 0.11 in serendipity but also shows higher relevance than the traditional relevance-pursuing baseline using TF-IDF.