FEVEROUS is a fact extraction and verification task that requires systems to extract evidence of both sentences and table cells from a Wikipedia dump, then predict the veracity of the given claim accordingly. Existing works extract evidence in the two formats separately, ignoring potential connections between them. In this paper, we propose a Unified Evidence Extraction model (UnifEE), which uses a mixed evidence graph to extract the evidence in both formats. With the carefully-designed unified evidence graph, UnifEE allows evidence interactions among all candidates in both formats at similar granularity. Experiments show that, with information aggregated from related evidence candidates in the fusion graph, UnifEE can make better decisions about which evidence should be kept, especially for claims requiring multi-hop reasoning or a combination of tables and texts. Thus it outperforms all previous evidence extraction methods and brings significant improvement in the subsequent claim verification step.

Prior research on dialogue state tracking (DST) is mostly based on written dialogue corpora. For spoken dialogues, the DST model trained on the written text should use the results (or hypothesis) of automatic speech recognition (ASR) as input. But ASR hypothesis often includes errors, which leads to significant performance drop for spoken dialogue state tracking. We address the issue by developing the following ASR error correction modules. First, we train a model to convert ASR hypothesis to ground truth user utterance, which can fix frequent patterns of errors. The model takes ASR hypotheses of two ASR models as input and fine-tuned in two stages. The corrected hypothesis is fed into a large scale pre-trained encoder-decoder model (T5) for DST training and inference. Second, if an output slot value from the encoder-decoder model is a name, we compare it with names in a dictionary crawled from Web sites and, if feasible, replace with the crawled name of the shortest edit distance. Third, we fix errors of temporal expressions in ASR hypothesis by using hand-crafted rules. Experiment results on the DSTC 11 speech-aware dataset, which is built on the popular MultiWOZ task (version 2.1), show that our proposed method can effectively mitigate the performance drop when moving from written text to spoken conversations.

The advent and fast development of neural networks have revolutionized the research on dialogue systems and subsequently have triggered various challenges regarding their automatic evaluation. Automatic evaluation of open-domain dialogue systems as an open challenge has been the center of the attention of many researchers. Despite the consistent efforts to improve automatic metrics’ correlations with human evaluation, there have been very few attempts to assess their robustness over multiple domains and dimensions. Also, their focus is mainly on the English language. All of these challenges prompt the development of automatic evaluation metrics that are reliable in various domains, dimensions, and languages. This track in the 11th Dialogue System Technology Challenge (DSTC11) is part of the ongoing effort to promote robust and multilingual automatic evaluation metrics. This article describes the datasets and baselines provided to participants and discusses the submission and result details of the two proposed subtasks.

Pretrained language models (LMs) have shown compelling performance on various downstream tasks, but unfortunately they require a tremendous amount of inference compute. Knowledge distillation finds a path to compress LMs to small ones with a teacher-student paradigm. However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs. While a few studies have been carried out to fill the gap, the curse is not yet well tackled. In this paper, we aim at lifting the curse of capacity gap via enlarging the capacity of the student without notably increasing the inference compute. Largely motivated by sparse activation regime of mixture of experts (MoE), we propose a mixture of minimal experts (MiniMoE), which imposes extra parameters to the student but introduces almost no additional inference compute. Experimental results on GLUE and CoNLL demonstrate the curse of capacity gap is lifted by the magic of MiniMoE to a large extent. MiniMoE also achieves the state-of-the-art performance at small FLOPs compared with a range of competitive baselines. With a compression rate as much as ~50×, MiniMoE preserves ~95% GLUE score of the teacher.

Although many large-scale knowledge bases (KBs) claim to contain multilingual information, their support for many non-English languages is often incomplete. This incompleteness gives birth to the task of cross-lingual question answering over knowledge base (xKBQA), which aims to answer questions in languages different from that of the provided KB. One of the major challenges facing xKBQA is the high cost of data annotation, leading to limited resources available for further exploration. Another challenge is mapping KB schemas and natural language expressions in the questions under cross-lingual settings. In this paper, we propose a novel approach for xKBQA in a reading comprehension paradigm. We convert KB subgraphs into passages to narrow the gap between KB schemas and questions, which enables our model to benefit from recent advances in multilingual pre-trained language models (MPLMs) and cross-lingual machine reading comprehension (xMRC). Specifically, we use MPLMs, with considerable knowledge of cross-lingual mappings, for cross-lingual reading comprehension. Existing high-quality xMRC datasets can be further utilized to finetune our model, greatly alleviating the data scarcity issue in xKBQA. Extensive experiments on two xKBQA datasets in 12 languages show that our approach outperforms various baselines and achieves strong few-shot and zero-shot performance. Our dataset and code are released for further research.

The multi-answer phenomenon, where a question may have multiple answers scattered in the document, can be well handled by humans but is challenging enough for machine reading comprehension (MRC) systems. Despite recent progress in multi-answer MRC, there lacks a systematic analysis of how this phenomenon arises and how to better address it. In this work, we design a taxonomy to categorize commonly-seen multi-answer MRC instances, with which we inspect three multi-answer datasets and analyze where the multi-answer challenge comes from. We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances. We find that some paradigms capture well the key information in the questions while others better model the relation between questions and contexts. We thus explore strategies to make the best of the strengths of different paradigms. Experiments show that generation models can be a promising platform to incorporate different paradigms. Our annotations and code are released for further research.

Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking. Although large language models (LLMs) succeed in many NLP tasks, it is still challenging for them to conduct complex causal reasoning like abductive reasoning and counterfactual reasoning. Given the fact that programming code may express causal relations more often and explicitly with conditional statements like “if“, we want to explore whether Code-LLMs acquire better causal reasoning abilities. Our experiments show that compared to text-only LLMs, Code-LLMs with code prompts are better causal reasoners. We further intervene on the prompts from different aspects, and discover that the key point is the programming structure. Code and data are available at https://github.com/xxxiaol/magic-if.

Recent advancements in reference-free learned metrics for open-domain dialogue evaluation have been driven by the progress in pre-trained language models and the availability of dialogue data with high-quality human annotations. However, current studies predominantly concentrate on English dialogues, and the generalization of these metrics to other languages has not been fully examined. This is largely due to the absence of a multilingual dialogue evaluation benchmark. To address the issue, we introduce xDial-Eval, built on top of open-source English dialogue evaluation datasets. xDial-Eval includes 12 turn-level and 6 dialogue-level English datasets, comprising 14930 annotated turns and 8691 annotated dialogues respectively. The English dialogue data are extended to nine other languages with commercial machine translation systems. On xDial-Eval, we conduct comprehensive analyses of previous BERT-based metrics and the recently-emerged large language models. Lastly, we establish strong self-supervised and multilingual baselines. In terms of average Pearson correlations over all datasets and languages, the best baseline outperforms OpenAI’s ChatGPT by absolute improvements of 6.5% and 4.6% at the turn and dialogue levels respectively, albeit with much fewer parameters. The data and code are publicly available at https://github.com/e0397123/xDial-Eval.

Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge graph (KG), which requires multiple steps of reasoning. Existing retrieval-based approaches solve this task by concentrating on the specific relation at different hops and predicting the intermediate entity within the reasoning path. However, these models fail to utilize information from head-tail entities and the semantic connection between relations to enhance the current relation representation, which undermines the information capturing of relations in KGs. To address this issue, we construct a dual relation graph where each node denotes a relation in the original KG (primal entity graph) and edges are constructed between relations sharing same head or tail entities. Then we iteratively do primal entity graph reasoning, dual relation graph information propagation, and interaction between these two graphs. In this way, the interaction between entity and relation is enhanced, and we derive better entity and relation representations. Experiments on two public datasets, WebQSP and CWQ, show that our approach achieves a significant performance gain over the prior state-of-the-art.

Structural bias has recently been exploited for aspect sentiment triplet extraction (ASTE) and led to improved performance. On the other hand, it is recognized that explicitly incorporating structural bias would have a negative impact on efficiency, whereas pretrained language models (PLMs) can already capture implicit structures. Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs? To answer the question, we propose to address the efficiency issues by using an adapter to integrate structural bias in the PLM and using a cheap-to-compute relative position structure in place of the syntactic dependency structure. Benchmarking evaluation is conducted on the SemEval datasets. The results show that our proposed structural adapter is beneficial to PLMs and achieves state-of-the-art performance over a range of strong baselines, yet with a light parameter demand and low latency. Meanwhile, we give rise to the concern that the current evaluation default with data of small scale is under-confident. Consequently, we release a large-scale dataset for ASTE. The results on the new dataset hint that the structural adapter is confidently effective and efficient to a large scale. Overall, we draw the conclusion that structural bias shall still be a necessity even with PLMs.

Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively few-shot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning makes pretrained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classification, we carry out in-depth analyses by progressively bridging the gap between prompt-tuning and commonly used finetuning. The summary is that the classifier structure and parameterization form the key to making good long-tailed learners, in comparison with the less important input structure. Finally, we verify the applicability of our finding to few-shot classification.

Recent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment. However, they either perform turn-level evaluation or look at a single dialogue quality dimension. One would expect a good evaluation metric to assess multiple quality dimensions at the dialogue level. To this end, we are motivated to propose a multi-dimensional dialogue-level metric, which consists of three sub-metrics with each targeting a specific dimension. The sub-metrics are trained with novel self-supervised objectives and exhibit strong correlations with human judgment for their respective dimensions. Moreover, we explore two approaches to combine the sub-metrics: metric ensemble and multitask learning. Both approaches yield a holistic metric that significantly outperforms individual sub-metrics. Compared to the existing state-of-the-art metric, the combined metrics achieve around 16% relative improvement on average across three high-quality dialogue-level evaluation benchmarks.

Recent advances in distilling pretrained language models have discovered that, besides the expressiveness of knowledge, the student-friendliness should be taken into consideration to realize a truly knowledgeable teacher. Based on a pilot study, we find that over-parameterized teachers can produce expressive yet student-unfriendly knowledge and are thus limited in overall knowledgeableness. To remove the parameters that result in student-unfriendliness, we propose a sparse teacher trick under the guidance of an overall knowledgeable score for each teacher parameter. The knowledgeable score is essentially an interpolation of the expressiveness and student-friendliness scores. The aim is to ensure that the expressive parameters are retained while the student-unfriendly ones are removed. Extensive experiments on the GLUE benchmark show that the proposed sparse teachers can be dense with knowledge and lead to students with compelling performance in comparison with a series of competitive baselines.

Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text summarization. However, there is a lack of systematic study on dialogue summarization systems. In this work, we first perform the fine-grained human analysis on the faithfulness of dialogue summaries and observe that over 35% of generated summaries are faithfully inconsistent respective the source dialogues. Furthermore, we present a new model-level faithfulness evaluation method. It examines generation models with multi-choice questions created by rule-based transformations. Experimental results show that our evaluation schema is a strong proxy for the factual correctness of summarization models. The human-annotated faithfulness samples and the evaluation toolkit are released to facilitate future research toward faithful dialogue summarization.

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.

Prompt tuning learns soft prompts to condition the frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner. While prompt tuning has gradually reached the performance level of fine-tuning as the model scale increases, there is still a large performance gap between prompt tuning and fine-tuning for models of moderate and small scales (typically less than 11B parameters). In this paper, we empirically show that the trained prompt tokens can have a negative impact on a downstream task and thus degrade its performance. To bridge the gap, we propose a novel Prompt tuning model with an eXtremely small scale (XPrompt) under the regime of lottery tickets hypothesis. Specifically, XPrompt eliminates the negative prompt tokens at different granularity levels through a hierarchical structured pruning, yielding a more parameter-efficient prompt yet with a competitive performance. Comprehensive experiments are carried out on the SuperGLUE tasks, and the results indicate that XPrompt is able to close the performance gap at smaller model scales.

Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie. We also propose an alignment loss to further integrate KG entities into the response generation network. Experiments on the large-scale REDIAL dataset demonstrate that the proposed system consistently outperforms state-of-the-art baselines.

This paper develops automatic song translation (AST) for tonal languages and addresses the unique challenge of aligning words’ tones with melody of a song in addition to conveying the original meaning. We propose three criteria for effective AST—preserving meaning, singability and intelligibility—and design metrics for these criteria. We develop a new benchmark for English–Mandarin song translation and develop an unsupervised AST system, Guided AliGnment for Automatic Song Translation (GagaST), which combines pre-training with three decoding constraints. Both automatic and human evaluations show GagaST successfully balances semantics and singability.

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM. Given two views of a text sample via weak and strong augmentation techniques, SFLM generates a pseudo label on the weakly augmented version. Then, the model predicts the same pseudo label when fine-tuned with the strongly augmented version. This simple approach is shown to outperform other state-of-the-art supervised and semi-supervised counterparts on six sentence classification and six sentence-pair classification benchmarking tasks. In addition, SFLM only relies on a few in-domain unlabeled data. We conduct a comprehensive analysis to demonstrate the robustness of our proposed approach under various settings, including augmentation techniques, model scale, and few-shot knowledge transfer across tasks.

In this paper, we present a new verification style reading comprehension dataset named VGaokao from Chinese Language tests of Gaokao. Different from existing efforts, the new dataset is originally designed for native speakers’ evaluation, thus requiring more advanced language understanding skills. To address the challenges in VGaokao, we propose a novel Extract-Integrate-Compete approach, which iteratively selects complementary evidence with a novel query updating mechanism and adaptively distills supportive evidence, followed by a pairwise competition to push models to learn the subtle difference among similar text pieces. Experiments show that our methods outperform various baselines on VGaokao with retrieved complementary evidence, while having the merits of efficiency and explainability. Our dataset and code are released for further research.

A dialogue is essentially a multi-turn interaction among interlocutors. Effective evaluation metrics should reflect the dynamics of such interaction. Existing automatic metrics are focused very much on the turn-level quality, while ignoring such dynamics. To this end, we propose DynaEval, a unified automatic evaluation framework which is not only capable of performing turn-level evaluation, but also holistically considers the quality of the entire dialogue. In DynaEval, the graph convolutional network (GCN) is adopted to model a dialogue in totality, where the graph nodes denote each individual utterance and the edges represent the dependency between pairs of utterances. A contrastive loss is then applied to distinguish well-formed dialogues from carefully constructed negative samples. Experiments show that DynaEval significantly outperforms the state-of-the-art dialogue coherence model, and correlates strongly with human judgements across multiple dialogue evaluation aspects at both turn and dialogue level.

In this work, we develop SimulSpeech, an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. SimulSpeech consists of a speech encoder, a speech segmenter and a text decoder, where 1) the segmenter builds upon the encoder and leverages a connectionist temporal classification (CTC) loss to split the input streaming speech in real time, 2) the encoder-decoder attention adopts a wait-k strategy for simultaneous translation. SimulSpeech is more challenging than previous cascaded systems (with simultaneous automatic speech recognition (ASR) and simultaneous neural machine translation (NMT)). We introduce two novel knowledge distillation methods to ensure the performance: 1) Attention-level knowledge distillation transfers the knowledge from the multiplication of the attention matrices of simultaneous NMT and ASR models to help the training of the attention mechanism in SimulSpeech; 2) Data-level knowledge distillation transfers the knowledge from the full-sentence NMT model and also reduces the complexity of data distribution to help on the optimization of SimulSpeech. Experiments on MuST-C English-Spanish and English-German spoken language translation datasets show that SimulSpeech achieves reasonable BLEU scores and lower delay compared to full-sentence end-to-end speech to text translation (without simultaneous translation), and better performance than the two-stage cascaded simultaneous translation model in terms of BLEU scores and translation delay.

Empathetic conversational models have been shown to improve user satisfaction and task outcomes in numerous domains. In Psychology, persona has been shown to be highly correlated to personality, which in turn influences empathy. In addition, our empirical analysis also suggests that persona plays an important role in empathetic conversations. To this end, we propose a new task towards persona-based empathetic conversations and present the first empirical study on the impact of persona on empathetic responding. Specifically, we first present a novel large-scale multi-domain dataset for persona-based empathetic conversations. We then propose CoBERT, an efficient BERT-based response selection model that obtains the state-of-the-art performance on our dataset. Finally, we conduct extensive experiments to investigate the impact of persona on empathetic responding. Notably, our results show that persona improves empathetic responding more when CoBERT is trained on empathetic conversations than non-empathetic ones, establishing an empirical link between persona and empathy in human conversations.

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is that it is memory-intensive and leads to unsatisfactory latency of user requests, raising the necessity of model compression. Existing solutions leverage the knowledge distillation framework to learn a smaller model that imitates the behaviors of BERT. However, the training procedure of knowledge distillation is expensive itself as it requires sufficient training data to imitate the teacher model. In this paper, we address this issue by proposing a tailored solution named LadaBERT (Lightweight adaptation of BERT through hybrid model compression), which combines the advantages of different model compression methods, including weight pruning, matrix factorization and knowledge distillation. LadaBERT achieves state-of-the-art accuracy on various public datasets while the training overheads can be reduced by an order of magnitude.

The state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of aspect-sentiment pairs lacks opinion terms as a reference, while co-extraction of aspect and opinion terms would not lead to meaningful pairs without determining their sentiment dependencies. To address the issue, we present a novel view of ABSA as an opinion triplet extraction task, and propose a multi-task learning framework to jointly extract aspect terms and opinion terms, and simultaneously parses sentiment dependencies between them with a biaffine scorer. At inference phase, the extraction of triplets is facilitated by a triplet decoding method based on the above outputs. We evaluate the proposed framework on four SemEval benchmarks for ASBA. The results demonstrate that our approach significantly outperforms a range of strong baselines and state-of-the-art approaches.

Due to their inherent capability in semantic alignment of aspects and their context words, attention mechanism and Convolutional Neural Networks (CNNs) are widely applied for aspect-based sentiment classification. However, these models lack a mechanism to account for relevant syntactical constraints and long-range word dependencies, and hence may mistakenly recognize syntactically irrelevant contextual words as clues for judging aspect sentiment. To tackle this problem, we propose to build a Graph Convolutional Network (GCN) over the dependency tree of a sentence to exploit syntactical information and word dependencies. Based on it, a novel aspect-specific sentiment classification framework is raised. Experiments on three benchmarking collections illustrate that our proposed model has comparable effectiveness to a range of state-of-the-art models, and further demonstrate that both syntactical information and long-range word dependencies are properly captured by the graph convolution structure.