Transactions of the Association for Computational Linguistics最新文献

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-12-01 DOI: 10.1162/tacl_a_00614

Jintao Wen, Geng Tu, Rui Li, Dazhi Jiang, Wenhua Zhu

{"title":"Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations","authors":"Jintao Wen, Geng Tu, Rui Li, Dazhi Jiang, Wenhua Zhu","doi":"10.1162/tacl_a_00614","DOIUrl":"https://doi.org/10.1162/tacl_a_00614","url":null,"abstract":"Abstract One-hot labels are commonly employed as ground truth in Emotion Recognition in Conversations (ERC). However, this approach may not fully encompass all the emotions conveyed in a single utterance, leading to suboptimal performance. Regrettably, current ERC datasets lack comprehensive emotionally distributed labels. To address this issue, we propose the Emotion Label Refinement (EmoLR) method, which utilizes context- and speaker-sensitive information to infer mixed emotional labels. EmoLR comprises an Emotion Predictor (EP) module and a Label Refinement (LR) module. The EP module recognizes emotions and provides context/speaker states for the LR module. Subsequently, the LR module calculates the similarity between these states and ground-truth labels, generating a refined label distribution (RLD). The RLD captures a more comprehensive range of emotions than the original one-hot labels. These refined labels are then used for model training in place of the one-hot labels. Experimental results on three public conversational datasets demonstrate that our EmoLR achieves state-of-the-art performance.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"88 3","pages":"1485-1499"},"PeriodicalIF":10.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139015511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis MissModal：提高多模态情感分析中缺失模态的鲁棒性

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-12-01 DOI: 10.1162/tacl_a_00628

Ronghao Lin, Haifeng Hu

{"title":"MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis","authors":"Ronghao Lin, Haifeng Hu","doi":"10.1162/tacl_a_00628","DOIUrl":"https://doi.org/10.1162/tacl_a_00628","url":null,"abstract":"Abstract When applying multimodal machine learning in downstream inference, both joint and coordinated multimodal representations rely on the complete presence of modalities as in training. However, modal-incomplete data, where certain modalities are missing, greatly reduces performance in Multimodal Sentiment Analysis (MSA) due to varying input forms and semantic information deficiencies. This limits the applicability of the predominant MSA methods in the real world, where the completeness of multimodal data is uncertain and variable. The generation-based methods attempt to generate the missing modality, yet they require complex hierarchical architecture with huge computational costs and struggle with the representation gaps across different modalities. Diversely, we propose a novel representation learning approach named MissModal, devoting to increasing robustness to missing modality in a classification approach. Specifically, we adopt constraints with geometric contrastive loss, distribution distance loss, and sentiment semantic loss to align the representations of modal-missing and modal-complete data, without impacting the sentiment inference for the complete modalities. Furthermore, we do not demand any changes in the multimodal fusion stage, highlighting the generality of our method in other multimodal learning systems. Extensive experiments demonstrate that the proposed method achieves superior performance with minimal computational costs in various missing modalities scenarios (flexibility), including severely missing modality (efficiency) on two public MSA datasets.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"81 1","pages":"1686-1702"},"PeriodicalIF":10.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138988172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

General then Personal: Decoupling and Pre-training for Personalized Headline Generation 先通用后个人：个性化标题生成的解耦与预训练

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-12-01 DOI: 10.1162/tacl_a_00621

Yun-Zhu Song, Yi-Syuan Chen, Lu Wang, Hong-Han Shuai

{"title":"General then Personal: Decoupling and Pre-training for Personalized Headline Generation","authors":"Yun-Zhu Song, Yi-Syuan Chen, Lu Wang, Hong-Han Shuai","doi":"10.1162/tacl_a_00621","DOIUrl":"https://doi.org/10.1162/tacl_a_00621","url":null,"abstract":"Abstract Personalized Headline Generation aims to generate unique headlines tailored to users’ browsing history. In this task, understanding user preferences from click history and incorporating them into headline generation pose challenges. Existing approaches typically rely on predefined styles as control codes, but personal style lacks explicit definition or enumeration, making it difficult to leverage traditional techniques. To tackle these challenges, we propose General Then Personal (GTP), a novel framework comprising user modeling, headline generation, and customization. We train the framework using tailored designs that emphasize two central ideas: (a) task decoupling and (b) model pre-training. With the decoupling mechanism separating the task into generation and customization, two mechanisms, i.e., information self-boosting and mask user modeling, are further introduced to facilitate the training and text control. Additionally, we introduce a new evaluation metric to address existing limitations. Extensive experiments conducted on the PENS dataset, considering both zero-shot and few-shot scenarios, demonstrate that GTP outperforms state-of-the-art methods. Furthermore, ablation studies and analysis emphasize the significance of decoupling and pre-training. Finally, the human evaluation validates the effectiveness of our approaches.1","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"449 ","pages":"1588-1607"},"PeriodicalIF":10.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138985900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training 通过正则化持续预训练消除预训练模型中的后门

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-12-01 DOI: 10.1162/tacl_a_00622

Biru Zhu, Ganqu Cui, Yangyi Chen, Yujia Qin, Lifan Yuan, Chong Fu, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu

{"title":"Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training","authors":"Biru Zhu, Ganqu Cui, Yangyi Chen, Yujia Qin, Lifan Yuan, Chong Fu, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu","doi":"10.1162/tacl_a_00622","DOIUrl":"https://doi.org/10.1162/tacl_a_00622","url":null,"abstract":"Abstract Recent research has revealed that pre-trained models (PTMs) are vulnerable to backdoor attacks before the fine-tuning stage. The attackers can implant transferable task-agnostic backdoors in PTMs, and control model outputs on any downstream task, which poses severe security threats to all downstream applications. Existing backdoor-removal defenses focus on task-specific classification models and they are not suitable for defending PTMs against task-agnostic backdoor attacks. To this end, we propose the first task-agnostic backdoor removal method for PTMs. Based on the selective activation phenomenon in backdoored PTMs, we design a simple and effective backdoor eraser, which continually pre-trains the backdoored PTMs with a regularization term in an end-to-end approach. The regularization term removes backdoor functionalities from PTMs while the continual pre-training maintains the normal functionalities of PTMs. We conduct extensive experiments on pre-trained models across different modalities and architectures. The experimental results show that our method can effectively remove backdoors inside PTMs and preserve benign functionalities of PTMs with a few downstream-task-irrelevant auxiliary data, e.g., unlabeled plain texts. The average attack success rate on three downstream datasets is reduced from 99.88% to 8.10% after our defense on the backdoored BERT. The codes are publicly available at https://github.com/thunlp/RECIPE.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"184 ","pages":"1608-1623"},"PeriodicalIF":10.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139013302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Efficient Self-Supervised Cross-View Training For Sentence Embedding 用于句子嵌入的高效自监督交叉视图训练

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-11-06 DOI: 10.1162/tacl_a_00620

Peerat Limkonchotiwat, Wuttikorn Ponwitayarat, Lalita Lowphansirikul, Can Udomcharoenchaikit, E. Chuangsuwanich, Sarana Nutanong

引用次数: 0

U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction U-CORE：用于开放关系提取的统一深度聚类对比框架

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-11-01 DOI: 10.1162/tacl_a_00604

Jie Zhou, Shenpo Dong, Yunxin Huang, Meihan Wu, Haili Li, Jingnan Wang, Hongkui Tu, Xiaodong Wang

{"title":"U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction","authors":"Jie Zhou, Shenpo Dong, Yunxin Huang, Meihan Wu, Haili Li, Jingnan Wang, Hongkui Tu, Xiaodong Wang","doi":"10.1162/tacl_a_00604","DOIUrl":"https://doi.org/10.1162/tacl_a_00604","url":null,"abstract":"Abstract Within Open Relation Extraction (ORE) tasks, the Zero-shot ORE method is to generalize undefined relations from predefined relations, while the Unsupervised ORE method is to extract undefined relations without the need for annotations. However, despite the possibility of overlap between predefined and undefined relations in the training data, a unified framework for both Zero-shot and Unsupervised ORE has yet to be established. To address this gap, we propose U-CORE: A Unified Deep Cluster-wise Contrastive Framework for both Zero-shot and Unsupervised ORE, by leveraging techniques from Contrastive Learning (CL) and Clustering.1 U-CORE overcomes the limitations of CL-based Zero-shot ORE methods by employing Cluster-wise CL that preserves both local smoothness as well as global semantics. Additionally, we employ a deep-cluster-based updater that optimizes the cluster center, thus enhancing the accuracy and efficiency of the model. To increase the stability of the model, we adopt Adaptive Self-paced Learning that effectively addresses the data-shifting problems. Experimental results on three well-known datasets demonstrate that U-CORE significantly improves upon existing methods by showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI on Unsupervised ORE tasks.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"5 1","pages":"1301-1315"},"PeriodicalIF":10.9,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139297367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR AfriSpeech-200：用于临床和通用领域 ASR 的泛非洲重音语音数据集

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-09-30 DOI: 10.1162/tacl_a_00627

Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, C. Emezue, Sahib Singh, Bonaventure F. P. Dossou, Joanne Osuchukwu, Salomey Osei, A. Tonja, Naome A. Etori, Clinton Mbataku

{"title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","authors":"Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli, C. Emezue, Sahib Singh, Bonaventure F. P. Dossou, Joanne Osuchukwu, Salomey Osei, A. Tonja, Naome A. Etori, Clinton Mbataku","doi":"10.1162/tacl_a_00627","DOIUrl":"https://doi.org/10.1162/tacl_a_00627","url":null,"abstract":"Abstract Africa has a very poor doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day—a heavy patient burden compared with developed countries—but productivity tools such as clinical automatic speech recognition (ASR) are lacking for these overworked clinicians. However, clinical ASR is mature, even ubiquitous, in developed nations, and clinician-reported performance of commercial clinical ASR systems is generally satisfactory. Furthermore, the recent performance of general domain ASR is approaching human accuracy. However, several gaps exist. Several publications have highlighted racial bias with speech-to-text algorithms and performance on minority accents lags significantly. To our knowledge, there is no publicly available research or benchmark on accented African clinical ASR, and speech data is non-existent for the majority of African accents. We release AfriSpeech, 200hrs of Pan-African English speech, 67,577 clips from 2,463 unique speakers across 120 indigenous accents from 13 countries for clinical and general domain ASR, a benchmark test set, with publicly available pre-trained models with SOTA performance on the AfriSpeech benchmark.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"89 1","pages":"1669-1685"},"PeriodicalIF":10.9,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139332019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages MIRACL:一个涵盖18种不同语言的多语言检索数据集

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-09-01 DOI: 10.1162/tacl_a_00595

Xinyu Crystina Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin

{"title":"MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages","authors":"Xinyu Crystina Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin","doi":"10.1162/tacl_a_00595","DOIUrl":"https://doi.org/10.1162/tacl_a_00595","url":null,"abstract":"Abstract MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world. This resource is designed to support monolingual retrieval tasks, where the queries and the corpora are in the same language. In total, we have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by our team. MIRACL covers languages that are both typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources. Extensive automatic heuristic verification and manual assessments were performed during the annotation process to control data quality. In total, MIRACL represents an investment of around five person-years of human annotator effort. Our goal is to spur research on improving retrieval across a continuum of languages, thus enhancing information access capabilities for diverse populations around the world, particularly those that have traditionally been underserved. MIRACL is available at http://miracl.ai/.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"1114-1131"},"PeriodicalIF":10.9,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"64440768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Shared Lexical Items as Triggers of Code Switching 共享词条是代码转换的触发器

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-08-29 DOI: 10.1162/tacl_a_00613

S. Wintner, Safaa Shehadi, Yuli Zeira, Doreen Osmelak, Yuval Nov

引用次数: 0

Can Authorship Representation Learning Capture Stylistic Features? 作者表征学习能否捕捉文体特征？

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-08-22 DOI: 10.1162/tacl_a_00610

Andrew Wang, Cristina Aggazzotti, R. Kotula, Rafael A. Rivera Soto, M. Bishop, Nicholas Andrews

{"title":"Can Authorship Representation Learning Capture Stylistic Features?","authors":"Andrew Wang, Cristina Aggazzotti, R. Kotula, Rafael A. Rivera Soto, M. Bishop, Nicholas Andrews","doi":"10.1162/tacl_a_00610","DOIUrl":"https://doi.org/10.1162/tacl_a_00610","url":null,"abstract":"Abstract Automatically disentangling an author’s style from the content of their writing is a longstanding and possibly insurmountable problem in computational linguistics. At the same time, the availability of large text corpora furnished with author labels has recently enabled learning authorship representations in a purely data-driven manner for authorship attribution, a task that ostensibly depends to a greater extent on encoding writing style than encoding content. However, success on this surrogate task does not ensure that such representations capture writing style since authorship could also be correlated with other latent variables, such as topic. In an effort to better understand the nature of the information these representations convey, and specifically to validate the hypothesis that they chiefly encode writing style, we systematically probe these representations through a series of targeted experiments. The results of these experiments suggest that representations learned for the surrogate authorship prediction task are indeed sensitive to writing style. As a consequence, authorship representations may be expected to be robust to certain kinds of data shift, such as topic drift over time. Additionally, our findings may open the door to downstream applications that require stylistic representations, such as style transfer.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"21 1","pages":"1416-1431"},"PeriodicalIF":10.9,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139349572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0