Although fine-tuning a pre-trained model with a conventional approach has shown to be effective in various downstream tasks, previous work has used only backpropagation to fine-tune the model, which causes a massive amount of computational resources and time. We propose Extreme Fine-Tuning (EFT), a novel approach for fine-tuning a pre-trained model effectively and efficiently. EFT uses backpropagation for a brief fine-tuning and an iterative extreme learning machine for training a classifier. We applied EFT to four text classification datasets, MELD, IEMOCAP, IMDb, and AG News, and compared its performance with state-of-the-art (SOTA) approaches. The results indicate that EFT noticeably outperformed the other approaches in training-time measurement with comparable model performance. We will release our code at https://github.com/up-33/extreme-fine-tuning.

Continual learning aims to accumulate knowledge to solve new tasks without catastrophic forgetting for previously learned tasks. Research on continual learning has led to the development of generative replay, which prevents catastrophic forgetting by generating pseudo-samples for previous tasks and learning them together with new tasks. Inspired by the biological brain, we propose the hippocampal memory indexing to enhance the generative replay by controlling sample generation using compressed features of previous training samples. It enables the generation of a specific training sample from previous tasks, thus improving the balance and quality of generated replay samples. Experimental results indicate that our method effectively controls the sample generation and consistently outperforms the performance of current generative replay methods.

Multimodal emotion recognition aims to recognize emotions for each utterance from multiple modalities, which has received increasing attention for its application in human-machine interaction. Current graph-based methods fail to simultaneously depict global contextual features and local diverse uni-modal features in a dialogue. Furthermore, with the number of graph layers increasing, they easily fall into over-smoothing. In this paper, we propose a method for joint modality fusion and graph contrastive learning for multimodal emotion recognition (Joyful), where multimodality fusion, contrastive learning, and emotion recognition are jointly optimized. Specifically, we first design a new multimodal fusion mechanism that can provide deep interaction and fusion between the global contextual and uni-modal specific features. Then, we introduce a graph contrastive learning framework with inter- and intra-view contrastive losses to learn more distinguishable representations for samples with different sentiments. Extensive experiments on three benchmark datasets indicate that Joyful achieved state-of-the-art (SOTA) performance compared with all baselines. Code is released on Github (https://anonymous.4open.science/r/MERC-7F88).

The purpose of feedback comment generation is to provide useful feedback comments for a wide range of errors in learners’ essays from a language learning perspective. Since it is difficult to obtain appropriate comments at a practical level with rule-based or retrieval- based methods, we explore neural-based gen- erative methods with pre-trained models. We further assume the effectiveness of consider- ing grammatical terms in generating feedback comments. Specifically, this paper proposes T5-based models using predicted grammati- cal terms, submitted to FCG GenChal, and presents their results. By using correct gram- matical terms, our model could improve the BLEU score by 19.0 points, compared with the baseline T5 without grammatical terms on the development dataset. Furthermore, by using predicted grammatical terms, our model could improve the manual evaluation score by 2.33 points, compared with the baseline T5 without grammatical terms on the test dataset.

The emergence of pre-trained language models has taken story generation, which is the task of automatically generating a comprehensible story from limited information, to a new stage. Although generated stories from the language models are fluent and grammatically correct, the lack of coherence affects their quality. We propose a knowledge-based multi-stage model that incorporates the schema, a kind of structured knowledge, to guide coherent story generation. Our framework includes a schema acquisition module, a plot generation module, and a surface realization module. In the schema acquisition module, high-relevant structured knowledge pieces are selected as a schema. In the plot generation module, a coherent plot plan is navigated by the schema. In the surface realization module, conditioned by the generated plot, a story is generated. Evaluations show that our methods can generate more comprehensible stories than strong baselines, especially with higher global coherence and less repetition.

This paper proposes a new second language learning task of generating a response including specified grammatical items. We consider two approaches: 1) fine-tuning a pre-trained language model (DialoGPT) by reinforcement learning and 2) providing a few-shot prompt to a large language model (GPT-3). For reinforcement learning, we examine combinations of three reward functions that consider grammatical items, diversity, and fluency. Our experiments confirm that both approaches can generate responses including the specified grammatical items and that it is crucial to consider fluency rather than diversity as the reward function.

Dataset distillation aims to create a small dataset of informative synthetic samples to rapidly train neural networks that retain the performance of the original dataset. In this paper, we focus on constructing distilled few-shot datasets for natural language processing (NLP) tasks to fine-tune pre-trained transformers. Specifically, we propose to introduce attention labels, which can efficiently distill the knowledge from the original dataset and transfer it to the transformer models via attention probabilities. We evaluated our dataset distillation methods in four various NLP tasks and demonstrated that it is possible to create distilled few-shot datasets with the attention labels, yielding impressive performances for fine-tuning BERT. Specifically, in AGNews, a four-class news classification task, our distilled few-shot dataset achieved up to 93.2% accuracy, which is 98.5% performance of the original dataset even with only one sample per class and only one gradient step.

Text infilling aims to restore incomplete texts by filling in blanks, which has attracted more attention recently because of its wide application in ancient text restoration and text rewriting. However, attribute- aware text infilling is yet to be explored, and existing methods seldom focus on the infilling length of each blank or the number/location of blanks. In this paper, we propose an Attribute-aware Text Infilling method via a Pre-trained language model (A-TIP), which contains a text infilling component and a plug- and-play discriminator. Specifically, we first design a unified text infilling component with modified attention mechanisms and intra- and inter-blank positional encoding to better perceive the number of blanks and the infilling length for each blank. Then, we propose a plug-and-play discriminator to guide generation towards the direction of improving attribute relevance without decreasing text fluency. Finally, automatic and human evaluations on three open-source datasets indicate that A-TIP achieves state-of- the-art performance compared with all baselines.

A repetition is a response that repeats words in the previous speaker’s utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.

Previous studies on the timeline summarization (TLS) task ignored the information interaction between sentences and dates, and adopted pre-defined unlearnable representations for them. They also considered date selection and event detection as two independent tasks, which makes it impossible to integrate their advantages and obtain a globally optimal summary. In this paper, we present a joint learning-based heterogeneous graph attention network for TLS (HeterTls), in which date selection and event detection are combined into a unified framework to improve the extraction accuracy and remove redundant sentences simultaneously. Our heterogeneous graph involves multiple types of nodes, the representations of which are iteratively learned across the heterogeneous graph attention layer. We evaluated our model on four datasets, and found that it significantly outperformed the current state-of-the-art baselines with regard to ROUGE scores and date selection metrics.

The task of generating weather-forecast comments from meteorological simulations has the following requirements: (i) the changes in numerical values for various physical quantities need to be considered, (ii) the weather comments should be dependent on delivery time and area information, and (iii) the comments should provide useful information for users. To meet these requirements, we propose a data-to-text model that incorporates three types of encoders for numerical forecast maps, observation data, and meta-data. We also introduce weather labels representing weather information, such as sunny and rain, for our model to explicitly describe useful information. We conducted automatic and human evaluations. The results indicate that our model performed best against baselines in terms of informativeness. We make our code and data publicly available.

Recent neural text generation models have shown significant improvement in generating descriptive text from structured data such as table formats. One of the remaining important challenges is generating more analytical descriptions that can be inferred from facts in a data source. The use of a template-based generator and a pointer-generator is among the potential alternatives for table-to-text generators. In this paper, we propose a framework consisting of a pre-trained model and a copy mechanism. The pre-trained models are fine-tuned to produce fluent text that is enriched with numerical reasoning. However, it still lacks fidelity to the table contents. The copy mechanism is incorporated in the fine-tuning step by using general placeholders to avoid producing hallucinated phrases that are not supported by a table while preserving high fluency. In summary, our contributions are (1) a new dataset for numerical table-to-text generation using pairs of a table and a paragraph of a table description with richer inference from scientific papers, and (2) a table-to-text generation framework enriched with numerical reasoning.

There has been very limited work on the adaptation of Part-Of-Speech (POS) tagging to learner English despite the fact that POS tagging is widely used in related tasks. In this paper, we explore how we can adapt POS tagging to learner English efficiently and effectively. Based on the discussion of possible causes of POS tagging errors in learner English, we show that deep neural models are particularly suitable for this. Considering the previous findings and the discussion, we introduce the design of our model based on bidirectional Long Short-Term Memory. In addition, we describe how to adapt it to a wide variety of native languages (potentially, hundreds of them). In the evaluation section, we empirically show that it is effective for POS tagging in learner English, achieving an accuracy of 0.964, which significantly outperforms the state-of-the-art POS-tagger. We further investigate the tagging results in detail, revealing which part of the model design does or does not improve the performance.

Dialogue breakdown detection is a promising technique in dialogue systems. To promote the research and development of such a technique, we organized a dialogue breakdown detection challenge where the task is to detect a system’s inappropriate utterances that lead to dialogue breakdowns in chat. This paper describes the design, datasets, and evaluation metrics for the challenge as well as the methods and results of the submitted runs of the participants.