EMNLP 2023 论文列表

Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with transfer learning using pre-trained models, including multilingual models trained on other languages. In some cases, even supervision data comes from other languages. Does cross-lingual transfer also import new biases? To answer this question, we use counterfactual evaluation to test whether gender or racial biases are imported when using cross-lingual transfer, compared to a monolingual transfer setting. Across five languages, we find that systems using cross-lingual transfer usually become more biased than their monolingual counterparts. We also find racial biases to be much more prevalent than gender biases. To spur further research on this topic, we release the sentiment models we used for this study, and the intermediate checkpoints throughout training, yielding 1,525 distinct models; we also release our evaluation code.

Question generation is a widely used data augmentation approach with extensive applications, and extracting qualified candidate answers from context passages is a critical step for most question generation systems. However, existing methods for candidate answer extraction are reliant on linguistic rules or annotated data that face the partial annotation issue and challenges in generalization. To overcome these limitations, we propose a novel unsupervised candidate answer extraction approach that leverages the inherent structure of context passages through a Differentiable Masker-Reconstructor (DMR) Model with the enforcement of self-consistency for picking up salient information tokens. We curated two datasets with exhaustively-annotated answers and benchmark a comprehensive set of supervised and unsupervised candidate answer extraction methods. We demonstrate the effectiveness of the DMR model by showing its performance is superior among unsupervised methods and comparable to supervised methods.

In the era of widespread dissemination through social media, the task of rumor detection plays a pivotal role in establishing a trustworthy and reliable information environment. Nonetheless, existing research on rumor detection confronts several challenges: the limited expressive power of text encoding sequences, difficulties in domain knowledge coverage and effective information extraction with knowledge graph-based methods, and insufficient mining of semantic structural information. To address these issues, we propose a Crowd Intelligence and ChatGPT-Assisted Network(CICAN) for rumor classification. Specifically, we present a crowd intelligence-based semantic feature learning module to capture textual content's sequential and hierarchical features. Then, we design a knowledge-based semantic structural mining module that leverages ChatGPT for knowledge enhancement. Finally, we construct an entity-sentence heterogeneous graph and design Entity-Aware Heterogeneous Attention to effectively integrate diverse structural information meta-paths. Experimental results demonstrate that CICAN achieves performance improvement in rumor detection tasks, validating the effectiveness and rationality of using large language models as auxiliary tools.

Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perception of reality isn't always faithful to the physical world. This raises a key question: do VLMs have the similar kind of illusions as humans do, or do they faithfully learn to represent reality? To investigate this question, we build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusions in state-of-the-art VLMs. Our findings have shown that although the overall alignment is low, larger models are closer to human perception and more susceptible to visual illusions. Our dataset and initial findings will promote a better understanding of visual illusions in humans and machines and provide a stepping stone for future computational models that can better align humans and machines in perceiving and communicating about the shared visual world. The code and data are available at [github.com/vl-illusion/dataset](https://github.com/vl-illusion/dataset).

This paper analyses two hitherto unstudied sites sharing state-backed disinformation, Reliable Recent News (rrn.world) and WarOnFakes (waronfakes.com), which publish content in Arabic, Chinese, English, French, German, and Spanish. We describe our content acquisition methodology and perform cross-site unsupervised topic clustering on the resulting multilingual dataset. We also perform linguistic and temporal analysis of the web page translations and topics over time, and investigate articles with false publication dates. We make publicly available this new dataset of 14,053 articles, annotated with each language version, and additional metadata such as links and images. The main contribution of this paper for the NLP community is in the novel dataset which enables studies of disinformation networks, and the training of NLP tools for disinformation detection.

We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci-Instruct helps alleviate the scarcity of relevant, high-quality materials science textual data available in the open literature, and HoneyBee is the first billion-parameter language model specialized to materials science. In MatSci-Instruct we improve the trustworthiness of generated data by prompting multiple commercially available large language models for generation with an Instructor module (e.g. Chat-GPT) and verification from an independent Verifier module (e.g. Claude). Using MatSci-Instruct, we construct a dataset of multiple tasks and measure the quality of our dataset along multiple dimensions, including accuracy against known facts, relevance to materials science, as well as completeness and reasonableness of the data. Moreover, we iteratively generate more targeted instructions and instruction-data in a finetuning-evaluation-feedback loop leading to progressively better performance for our finetuned HoneyBee models. Our evaluation on the MatSci-NLP benchmark shows HoneyBee's outperformance of existing language models on materials science tasks and iterative improvement in successive stages of instruction-data refinement. We study the quality of HoneyBee's language modeling through automatic evaluation and analyze case studies to further understand the model's capabilities and limitations. Our code and relevant datasets are publicly available at https://github.com/BangLab-UdeM-Mila/NLP4MatSci-HoneyBee.

Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model (PLM) to generate style-transferred texts word by word in an autoregressive manner. However, such a generation process is less controllable and early prediction errors may affect future word predictions. In this paper, we propose a prompt-based editing approach to text style transfer. Specifically, we prompt a PLM for style classification and use the classification probability to compute a style score. Then, we perform discrete search with word-level editing to maximize a comprehensive scoring function for the style-transfer task. In this way, we transform a prompt-based generation problem into a classification one, which does not suffer from the error accumulation problem and is more controllable than the autoregressive generation of sentences. In our experiments, we performed both automatic and human evaluation on three style-transfer benchmark datasets, and show that our approach largely outperforms the existing systems that have 20 times more parameters. Additional empirical analyses further demonstrate the effectiveness of our approach.

Multilingual biomedical entity linking (MBEL) aims to map language-specific mentions in the biomedical text to standardized concepts in a multilingual knowledge base (KB) such as Unified Medical Language System (UMLS). In this paper, we propose Con2GEN, a prompt-based controllable contrastive generation framework for MBEL, which summarizes multidimensional information of the UMLS concept mentioned in biomedical text into a natural sentence following a predefined template. Instead of tackling the MBEL problem with a discriminative classifier, we formulate it as a sequence-to-sequence generation task, which better exploits the shared dependencies between source mentions and target entities. Moreover, Con2GEN matches against UMLS concepts in as many languages and types as possible, hence facilitating cross-information disambiguation. Extensive experiments show that our model achieves promising performance improvements compared with several state-of-the-art techniques on the XL-BEL and the Mantra GSC datasets spanning 12 typologically diverse languages.

Multilingualism is widespread around the world and code-switching (CSW) is a common practice among different language pairs/tuples across locations and regions. However, there is still not much progress in building successful CSW systems, despite the recent advances in Massive Multilingual Language Models (MMLMs). We investigate the reasons behind this setback through a critical study about the existing CSW data sets (68) across language pairs in terms of the collection and preparation (e.g. transcription and annotation) stages. This in-depth analysis reveals that \textbf{a)} most CSW data involves English ignoring other language pairs/tuples \textbf{b)} there are flaws in terms of representativeness in data collection and preparation stages due to ignoring the location based, socio-demographic and register variation in CSW. In addition, lack of clarity on the data selection and filtering stages shadow the representativeness of CSW data sets. We conclude by providing a short check-list to improve the representativeness for forthcoming studies involving CSW data collection and preparation.

By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the collapsing problem, where all experts eventually learn similar representations. However, this strategy has two key limitations: (i) the policy derived from random routers might be sub-optimal, and (ii) it requires extensive resources during training and evaluation, leading to limited efficiency gains. This work introduces \texttt{HyperRouter}, which dynamically generates the router's parameters through a fixed hypernetwork and trainable embeddings to achieve a balance between training the routers and freezing them to learn an improved routing policy. Extensive experiments across a wide range of tasks demonstrate the superior performance and efficiency gains of \texttt{HyperRouter} compared to existing routing methods. Our implementation is publicly available at {\url{{https://github.com/giangdip2410/HyperRouter}}}.

The ability to identify important entities in a text, known as Named Entity Recognition (NER), is useful in a large variety of downstream tasks in the biomedical domain. This is a considerably difficult task when working with Consumer Health Questions (CHQs), which consist of informal language used in day-to-day life by patients. These difficulties are amplified in the case of Bengali, which allows for a huge amount of flexibility in sentence structures and has significant variances in regional dialects. Unfortunately, the complexity of the language is not accurately reflected in the limited amount of available data, which makes it difficult to build a reliable decision-making system. To address the scarcity of data, this paper presents 'Bangla-HealthNER', a comprehensive dataset designed to identify named entities in health-related texts in the Bengali language. It consists of 31,783 samples sourced from a popular online public health platform, which allows it to capture the diverse range of linguistic styles and dialects used by native speakers from various regions in their day-to-day lives. The insight into this diversity in language will prove useful to any medical decision-making systems that are developed for use in real-world applications. To highlight the difficulty of the dataset, it has been benchmarked on state-of-the-art token classification models, where BanglishBERT achieved the highest performance with an F1-score of $56.13 \pm 0.75$%. The dataset and all relevant code used in this work have been made publicly available.

An attractive blog headline on social media platforms can immediately grab readers and trigger more clicks. However, a good headline shall not only contract the main content but also be eye-catchy with domain platform features, which are decided by the website’s users and objectives. With effective headlines, bloggers can obtain more site traffic and profits, while readers can have easier access to topics of interest. In this paper, we propose a disentanglement-based headline generation model: MediaHG (Social Media Headline Generation), which can balance the content and contextual features. Specifically, we first devise a sample module for various document views and generate the corresponding headline candidates. Then, we incorporate contrastive learning and auxiliary multi-task to choose the best domain-suitable headline, according to the disentangled budgets. Besides, our separated processing gains more flexible adaptation for other headline generation tasks with special domain features. Our model is built from the content and headlines of 70k hot posts collected from REDBook, a Chinese social media platform for daily sharing. Experimental results with language metrics ROUGE and human evaluation show the improvement in the headline generation task for the platform.

While large language models (LLMs) can answer many questions correctly, they can also hallucinate and give wrong answers. Wikidata, with its over 12 billion facts, can be used to ground LLMs to improve their factuality. This paper presents WikiWebQuestions, a high-quality question answering benchmark for Wikidata. Ported over from WebQuestions for Freebase, it consists of real-world data with SPARQL annotation. This paper presents a few-shot sequence-to-sequence semantic parser for Wikidata. We modify SPARQL to use the unique domain and property names instead of their IDs. We train the parser to use either the results from an entity linker or mentions in the query. We fine-tune LLaMA by adding the few-shot training data to that used to fine-tune Alpaca. Our experimental results demonstrate the effectiveness of this methodology, establishing a strong baseline of 76% and 65% answer accuracy in the dev and test sets of WikiWebQuestions, respectively. By pairing our semantic parser with GPT-3, we combine verifiable results with qualified GPT-3 guesses to provide useful answers to 96% of the questions in dev. We also show that our method outperforms the state-of-the-art for the QALD-7 Wikidata dataset by 3.6% in F1 score.

Deep neural networks have been widely applied in real-world scenarios, such as product restrictions on e-commerce and hate speech monitoring on social media, to ensure secure governance of various platforms. However, illegal merchants often deceive the detection models by adding large-scale perturbations to prohibited products, so as to earn illegal profits. Current adversarial attacks using imperceptible perturbations encounter challenges in simulating such adversarial behavior and evaluating the vulnerabilities of detection models to such perturbations. To address this issue, we propose a novel black-box multimodal attack, termed Sparse Multimodal Attack (SparseMA), which leverages sparse perturbations to simulate the adversarial behavior exhibited by illegal merchants in the black-box scenario. Moreover, SparseMA bridges the gap between images and texts by treating the separated image patches and text words uniformly in the discrete space. Extensive experiments demonstrate that SparseMA can identify the vulnerability of the model to different modalities, outperforming existing multimodal attacks and unimodal attacks. SparseMA, which is the first proposed method for black-box multimodal attacks to our knowledge, would be used as an effective tool for evaluating the robustness of multimodal models to different modalities.

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. LLMs are generally trained on publicly available text and code and cannot be expected to directly generalize to domain-specific parsing tasks in a zero-shot setting. In this work, we propose ZEROTOP, a zero-shot task-oriented parsing method that decomposes semantic parsing problem into a set of abstractive and extractive question-answering (QA) problems. For each utterance, we prompt the LLM with questions corresponding to its top-level intent and a set of slots and use the LLM generations to construct the target meaning representation. We observe that current LLMs fail to detect unanswerable questions; and as a result, cannot handle questions corresponding to missing slots. We address this by fine-tuning a language model on public QA datasets using synthetic negative samples. Experimental results show that our QA-based decomposition paired with the fine-tuned LLM can zero-shot parse ≈ 16% of utterances in the MTOP dataset.

The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.

Visual storytelling aims to generate compelling narratives from image sequences. Existing models often focus on enhancing the representation of the image sequence, e.g., with external knowledge sources or advanced graph structures. Despite recent progress, the stories are often repetitive, illogical, and lacking in detail. To mitigate these issues, we present a novel framework which integrates visual representations with pretrained language models and planning. Our model translates the image sequence into a visual prefix, a sequence of continuous embeddings which language models can interpret. It also leverages a sequence of question-answer pairs as a blueprint plan for selecting salient visual concepts and determining how they should be assembled into a narrative. Automatic and human evaluation on the VIST benchmark demonstrates that blueprint-based models generate stories that are more coherent, interesting, and natural compared to competitive baselines and state-of-the-art systems.

Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic data, pretraining on it, and then fine-tuning on real datasets; performance gains have been achieved either by ensembling or by using huge pretrained models such as XXL-T5 as the backbone. In this work, we explore an orthogonal direction: how to use available data more efficiently. First, we propose auxiliary tasks that exploit the alignment between the original and corrected sentences, such as predicting a sequence of corrections. We formulate each task as a sequence-to-sequence problem and perform multi-task training. Second, we discover that the order of datasets used for training and even individual instances within a dataset may have important effects on the final performance, so we set out to find the best training schedule. Together, these two ideas lead to significant improvements, producing results that improve state of the art with much smaller models; in particular, we outperform the best models based on T5-XXL (11B parameters) with a BART-based model (400M parameters).

Despite the impressive performance achieved by pre-trained language-and-vision models in downstream tasks, it remains an open question whether this reflects a proper understanding of image-text interaction. In this work, we explore to what extent they handle basic linguistic constructions---active-passive voice, coordination, and relative clauses---that even preschool children can typically master. We present BLA, a novel, automatically constructed benchmark to evaluate multimodal models on these Basic Language Abilities. We show that different types of Transformer-based systems, such as CLIP, ViLBERT, and BLIP2, generally struggle with BLA in a zero-shot setting, in line with previous findings. Our experiments, in particular, show that most of the tested models only marginally benefit when fine-tuned or prompted with construction-specific samples. Yet, the generative BLIP2 shows promising trends, especially in an in-context learning setting. This opens the door to using BLA not only as an evaluation benchmark but also to improve models' basic language abilities.