EMNLP 2023 论文列表

3D referring expression comprehension is a task to ground text representations onto objects in 3D scenes. It is a crucial task for indoor household robots or augmented reality devices to localize objects referred to in user instructions. However, existing indoor 3D referring expression comprehension datasets typically cover larger object classes that are easy to localize, such as chairs, tables, or doors, and often overlook small objects, such as cooking tools or office supplies. Based on the recently proposed diverse and high-resolution 3D scene dataset of ARKitScenes, we construct the ARKitSceneRefer dataset focusing on small daily-use objects that frequently appear in real-world indoor scenes. ARKitSceneRefer contains 15k objects of 1,605 indoor scenes, which are significantly larger than those of the existing 3D referring datasets, and covers diverse object classes of 583 from the LVIS dataset. In empirical experiments with both 2D and 3D state-of-the-art referring expression comprehension models, we observed the task difficulty of the localization in the diverse small object classes.

In this study, we highlight the importance of enhancing the quality of pretraining data in multilingual language models. Existing web crawls have demonstrated quality issues, particularly in the context of low-resource languages. Consequently, we introduce a new multilingual pretraining corpus for $16$ African languages, designed by carefully auditing existing pretraining corpora to understand and rectify prevalent quality issues. To compile this dataset, we undertake a rigorous examination of current data sources for thirteen languages within one of the most extensive multilingual web crawls, mC4, and extract cleaner data through meticulous auditing and improved web crawling strategies. Subsequently, we pretrain a new T5-based model on this dataset and evaluate its performance on multiple downstream tasks. Our model demonstrates better downstream effectiveness over existing pretrained models across four NLP tasks, underscoring the critical role data quality plays in pretraining language models in low-resource scenarios. Specifically, on cross-lingual QA evaluation, our new model is more than twice as effective as multilingual T5. All code, data and models are publicly available at https://github.com/castorini/AfriTeVa-keji.

The Universal Transformer (UT) is a variant of the Transformer that shares parameters across its layers and is Turing-complete under certain assumptions. Empirical evidence also shows that UTs have better compositional generalization than Vanilla Transformers (VTs) in formal language tasks. The parameter-sharing also affords it better parameter efficiency than VTs. Despite its many advantages, most state-of-the-art NLP systems use VTs as their backbone model instead of UTs. This is mainly because scaling UT parameters is more compute and memory intensive than scaling up a VT. This paper proposes the Sparse Universal Transformer (SUT), which leverages Sparse Mixture of Experts (SMoE) to reduce UT's computation complexity while retaining its parameter efficiency and generalization ability. Experiments show that SUT combines the best of both worlds, achieving strong generalization results on formal language tasks (Logical inference and CFQ) and impressive parameter and computation efficiency on standard natural language benchmarks like WMT'14.

This paper addresses the problem of generating questions from a given context and an answer, specifically focusing on questions that require multi-hop reasoning across an extended context. Previous studies have suggested that key phrase selection is essential for question generation (QG), yet it is still challenging to connect such disjointed phrases into meaningful questions, particularly for long context. To mitigate this issue, we propose MultiFactor, a novel QG framework based on multi-level content planning. Specifically, MultiFactor includes two components: FA-Model, which simultaneously selects key phrases and generates full answers, and Q-Model which takes the generated full answer as an additional input to generate questions. Here, full answer generation is introduced to connect the short answer with the selected key phrases, thus forming an answer-aware summary to facilitate QG. Both FA-Model and Q-Model are formalized as simple-yet-effective Phrase-Enhanced Transformers, our joint model for phrase selection and text generation. Experimental results show that our method outperforms strong baselines on two popular QG datasets. Our code is available at https://github.com/zeaver/MultiFactor.

The emergence of Large Language Models (LLMs), such as ChatGPT, has revolutionized general natural language preprocessing (NLP) tasks. However, their expertise in the financial domain lacks a comprehensive evaluation. To assess the ability of LLMs to solve financial NLP tasks, we present FinLMEval, a framework for Financial Language Model Evaluation, comprising nine datasets designed to evaluate the performance of language models. This study compares the performance of fine-tuned auto-encoding language models (BERT, RoBERTa, FinBERT) and the LLM ChatGPT. Our findings reveal that while ChatGPT demonstrates notable performance across most financial tasks, it generally lags behind the fine-tuned expert models, especially when dealing with proprietary datasets. We hope this study builds foundation evaluation benchmarks for continuing efforts to build more advanced LLMs in the financial domain.

Hallucination is a well-known phenomenon in text generated by large language models (LLMs). The existence of hallucinatory responses is found in almost all application scenarios e.g., summarization, question-answering (QA) etc. For applications requiring high reliability (e.g., customer-facing assistants), the potential existence of hallucination in LLM-generated text is a critical problem. The amount of hallucination can be reduced by leveraging information retrieval to provide relevant background information to the LLM. However, LLMs can still generate hallucinatory content for various reasons (e.g., prioritizing its parametric knowledge over the context, failure to capture the relevant information from the context, etc.). Detecting hallucinations through automated methods is thus paramount. To facilitate research in this direction, we introduce a sophisticated dataset, DelucionQA, that captures hallucinations made by retrieval-augmented LLMs for a domain-specific QA task. Furthermore, we propose a set of hallucination detection methods to serve as baselines for future works from the research community. Analysis and case study are also provided to share valuable insights on hallucination phenomena in the target scenario.

While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperative text game with Theory of Mind (ToM) inference tasks, comparing their performance with Multi-Agent Reinforcement Learning (MARL) and planning-based baselines. We observed evidence of emergent collaborative behaviors and high-order Theory of Mind capabilities among LLM-based agents. Our results reveal limitations in LLM-based agents' planning optimization due to systematic failures in managing long-horizon contexts and hallucination about the task state. We explore the use of explicit belief state representations to mitigate these issues, finding that it enhances task performance and the accuracy of ToM inferences for LLM-based agents.

Language understanding is a multi-faceted cognitive capability, which the Natural Language Processing (NLP) community has striven to model computationally for decades. Traditionally, facets of linguistic intelligence have been compartmentalized into tasks with specialized model architectures and corresponding evaluation protocols. With the advent of large language models (LLMs) the community has witnessed a dramatic shift towards general purpose, task-agnostic approaches powered by generative models. As a consequence, the traditional compartmentalized notion of language tasks is breaking down, followed by an increasing challenge for evaluation and analysis. At the same time, LLMs are being deployed in more real-world scenarios, including previously unforeseen zero-shot setups, increasing the need for trustworthy and reliable systems. Therefore, we argue that it is time to rethink what constitutes tasks and model evaluation in NLP, and pursue a more holistic view on language, placing trustworthiness at the center. Towards this goal, we review existing compartmentalized approaches for understanding the origins of a model's functional capacity, and provide recommendations for more multi-faceted evaluation protocols.

Over recent decades, significant advancements in cross-modal retrieval is mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), which hinders retrieval performance due to the inseparability of these representations. In our study, we first empirically validate the presence of the representation degeneration problem across multiple cross-modal benchmarks and methods. Next, to address it, we introduce a novel method, called InvGC, a post-processing technique inspired by graph convolution and average pooling. Specifically, InvGC defines the graph topology within the datasets and then applies graph convolution in a subtractive manner. This method effectively separates representations by increasing the distances between data points. To improve the efficiency and effectiveness of InvGC, we propose an advanced graph topology, LocalAdj, which only aims to increase the distances between each data point and its nearest neighbors. To understand why InvGC works, we present a detailed theoretical analysis, proving that the lower bound of recall will be improved after deploying InvGC. Extensive empirical results show that InvGC and InvGC w/LocalAdj significantly mitigate the representation degeneration problem, thereby enhancing retrieval performance.

Most of the recent work in leveraging Large Language Models (LLMs) such as GPT-3 for Machine Translation (MT) has focused on selecting the few-shot samples for prompting. In this work, we try to better understand the role of demonstration attributes for the in-context learning of translations through perturbations of high-quality, in-domain demonstrations. We find that asymmetric perturbation of the source-target mappings yield vastly different results. We show that the perturbation of the source side has surprisingly little impact, while target perturbation can drastically reduce translation quality, suggesting that it is the output text distribution that provides the most important learning signal during in-context learning of translations. We propose a method named Zero-Shot-Context to add this signal automatically in Zero-Shot prompting. We demonstrate that it improves upon the zero-shot translation performance of GPT-3, even making it competitive with few-shot prompted translations.

Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations. However, it can be challenging to determine what information to retrieve when the user is passive and does not express a clear need or request. To tackle this issue, we present a novel approach that focuses on generating internet search queries that are guided by social commonsense. Specifically, we leverage a commonsense dialog system to establish connections related to the conversation topic, which subsequently guides our query generation. Our proposed framework addresses passive user interactions by integrating topic tracking, commonsense response generation and instruction-driven query generation. Through extensive evaluations, we show that our approach overcomes limitations of existing query generation techniques that rely solely on explicit dialog information, and produces search queries that are more relevant, specific, and compelling, ultimately resulting in more engaging responses.

Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they either suffer from the erroneous (noisy) pseudo mappings or largely ignore the uncertainty of pseudo mappings. In this paper, we propose a novel semi-supervised EA method, termed as MixTEA, which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings. We firstly train a student model using few labeled mappings as standard. More importantly, in pseudo mapping learning, we propose a bi-directional voting (BDV) strategy that fuses the alignment decisions in different directions to estimate the uncertainty via the joint matching confidence score. Meanwhile, we also design a matching diversity-based rectification (MDR) module to adjust the pseudo mapping learning, thus reducing the negative influence of noisy mappings. Extensive results on benchmark datasets as well as further analyses demonstrate the superiority and the effectiveness of our proposed method.

Zero-shot stance detection (ZSSD) aims to determine whether the author of a text is in favor of, against, or neutral toward a target that is unseen during training. In this paper, we present EZ-STANCE, a large English ZSSD dataset with 30,606 annotated text-target pairs. In contrast to VAST, the only other existing ZSSD dataset, EZ-STANCE includes both noun-phrase targets and claim targets, covering a wide range of domains. In addition, we introduce two challenging subtasks for ZSSD: target-based ZSSD and domain-based ZSSD. We provide an in-depth description and analysis of our dataset. We evaluate EZ-STANCE using state-of-the-art deep learning models. Furthermore, we propose to transform ZSSD into the NLI task by applying two simple yet effective prompts to noun-phrase targets. Our experimental results show that EZ-STANCE is a challenging new benchmark, which provides significant research opportunities on ZSSD. We will make our dataset and code available on GitHub.

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit supervision, complex model architectures, or massive external models. We present $\texttt{ABEL}$, a simple but effective unsupervised method to enhance passage retrieval in zero-shot settings. Our technique follows a straightforward loop: a dense retriever learns from supervision signals provided by a reranker, and subsequently, the reranker is updated based on feedback from the improved retriever. By iterating this loop, the two components mutually enhance one another's performance. Experimental results demonstrate that our unsupervised $\texttt{ABEL}$ model outperforms both leading supervised and unsupervised retrievers on the BEIR benchmark. Meanwhile, it exhibits strong adaptation abilities to tasks and domains that were unseen during training. By either fine-tuning $\texttt{ABEL}$ on labelled data or integrating it with existing supervised dense retrievers, we achieve state-of-the-art results.\footnote{Source code is available at \url{https://github.com/Fantabulous-J/BootSwitch}.}

Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for long-form videos. These videos contain massive visual tokens due to their inherent 3D properties and spatiotemporal redundancy, making it challenging to capture complex temporal and spatial relationships. To tackle this issue, we propose an efficient method called TEmporal-Spatial Token Aggregation (TESTA). TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. TESTA can reduce the number of visual tokens by 75% and thus accelerate video encoding. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video encoder block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks. Experimental results show that TESTA improves computing efficiency by 1.7 times, and achieves significant performance gains from its scalability in processing longer input frames, e.g., +13.7 R@1 on QuerYD and +6.5 R@1 on Condensed Movie.

Despite exciting recent results showing vision-language systems’ capacity to reason about images using natural language, their capacity for video reasoning remains underexplored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language while alleviating the computational complexities of processing videos. To evaluate this novel application, we introduce VIP, an inference-time challenge dataset designed to explore models’ reasoning capabilities through video chain-of-thought. Inspired by visually descriptive scene plays, we propose two formats for keyframe description: unstructured dense captions and structured scene descriptions that identify the focus, action, mood, objects, and setting (FAMOuS) of the keyframe. To evaluate video reasoning, we propose two tasks: Video Infilling and Video Prediction, which test abilities to generate multiple intermediate keyframes and predict future keyframes, respectively. We benchmark GPT-4, GPT-3, and VICUNA on VIP, demonstrate the performance gap in these complex video reasoning tasks, and encourage future work to prioritize language models for efficient and generalized video reasoning.

ChatGPT's emergence heralds a transformative phase in NLP, particularly demonstrated through its excellent performance on many English benchmarks. However, the model's efficacy across diverse linguistic contexts remains largely uncharted territory. This work aims to bridge this knowledge gap, with a primary focus on assessing ChatGPT's capabilities on Arabic languages and dialectal varieties. Our comprehensive study conducts a large-scale automated and human evaluation of ChatGPT, encompassing 44 distinct language understanding and generation tasks on over 60 different datasets. To our knowledge, this marks the first extensive performance analysis of ChatGPT's deployment in Arabic NLP. Our findings indicate that, despite its remarkable performance in English, ChatGPT is consistently surpassed by smaller models that have undergone finetuning on Arabic. We further undertake a meticulous comparison of ChatGPT and GPT-4's Modern Standard Arabic (MSA) and Dialectal Arabic (DA), unveiling the relative shortcomings of both models in handling Arabic dialects compared to MSA. Although we further explore and confirm the utility of employing GPT-4 as a potential alternative for human evaluation, our work adds to a growing body of research underscoring the limitations of ChatGPT.

Aspect Sentiment Triplet Extraction (ASTE) is one of the compound tasks of fine-grained aspect-based sentiment analysis (ABSA), aiming at extracting the triplets of aspect terms, corresponding opinion terms and the associated sentiment orientation. Recent efforts in exploiting span-level semantic interaction shown superior performance on ASTE task. However, most of the existing span-based approaches suffer from enumerating all possible spans, since it can introduce too much noise in sentiment triplet extraction. To ease this burden, we propose a dual-channel span generation method to coherently constrain the search space of span candidates. Specifically, we leverage the syntactic relations among aspect/opinion terms and the associated part-of-speech characteristics in those terms to generate span candidates, which reduces span enumeration by nearly half. Besides, feature representations are learned from syntactic and part-of-speech correlation among terms, which renders span representation fruitful linguistic information. Extensive experiments on two versions of public datasets demonstrate both the effectiveness of our design and the superiority on ASTE/ATE/OTE tasks~\footnote{We release our code at \url{https://github.com/bert-ply/Dual_Span}}.

Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided text document, or whether they can benefit from additional temporal information extracted using other systems. We address this research question by applying existing temporal information extraction systems to construct temporal graphs of events, times, and temporal relations in questions and documents. We then investigate different approaches for fusing these graphs into Transformer models. Experimental results show that our proposed approach for fusing temporal graphs into input text substantially enhances the temporal reasoning capabilities of Transformer models with or without fine-tuning. Additionally, our proposed method outperforms various graph convolution-based approaches and establishes a new state-of-the-art performance on SituatedQA and three splits of TimeQA.