Annual Meeting of the Association for Computational Linguistics最新文献

Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance 利用上下文线索和角色相关性增强文档级事件参数提取

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-10-08 DOI: 10.18653/v1/2023.findings-acl.817

Wanlong Liu, Shaohuan Cheng, Di Zeng, Hong Qu

{"title":"Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance","authors":"Wanlong Liu, Shaohuan Cheng, Di Zeng, Hong Qu","doi":"10.18653/v1/2023.findings-acl.817","DOIUrl":"https://doi.org/10.18653/v1/2023.findings-acl.817","url":null,"abstract":"Document-level event argument extraction poses new challenges of long input and cross-sentence inference compared to its sentence-level counterpart. However, most prior works focus on capturing the relations between candidate arguments and the event trigger in each event, ignoring two crucial points: a) non-argument contextual clue information; b) the relevance among argument roles. In this paper, we propose a SCPRG (Span-trigger-based Contextual Pooling and latent Role Guidance) model, which contains two novel and effective modules for the above problem. The Span-Trigger-based Contextual Pooling(STCP) adaptively selects and aggregates the information of non-argument clue words based on the context attention weights of specific argument-trigger pairs from pre-trained model. The Role-based Latent Information Guidance (RLIG) module constructs latent role representations, makes them interact through role-interactive encoding to capture semantic relevance, and merges them into candidate arguments. Both STCP and RLIG introduce no more than 1% new parameters compared with the base model and can be easily applied to other event extraction models, which are compact and transplantable. Experiments on two public datasets show that our SCPRG outperforms previous state-of-the-art methods, with 1.13 F1 and 2.64 F1 improvements on RAMS and WikiEvents respectively. Further analyses illustrate the interpretability of our model.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128518032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

How-to Guides for Specific Audiences: A Corpus and Initial Findings 特定受众指南:语料库和初步发现

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-09-21 DOI: 10.18653/v1/2023.acl-srw.46

Nicola Fanton, Agnieszka Falenska, Michael Roth

引用次数: 0

Substitution-based Semantic Change Detection using Contextual Embeddings 基于替换的基于上下文嵌入的语义变化检测

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-09-05 DOI: 10.18653/v1/2023.acl-short.52

Dallas Card

引用次数: 1

MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning MultiCapCLIP:自动编码提示零镜头多语言视觉字幕

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-08-25 DOI: 10.18653/v1/2023.acl-long.664

Bang Yang, Fenglin Liu, X. Wu, Yaowei Wang, Xu Sun, Yuexian Zou

{"title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","authors":"Bang Yang, Fenglin Liu, X. Wu, Yaowei Wang, Xu Sun, Yuexian Zou","doi":"10.18653/v1/2023.acl-long.664","DOIUrl":"https://doi.org/10.18653/v1/2023.acl-long.664","url":null,"abstract":"Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126093612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation 领域对抗学习增强元自训练的领域适应

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-08-05 DOI: 10.18653/v1/2023.acl-long.92

Menglong Lu, Zhen Huang, Yunxiang Zhao, Zhiliang Tian, Yang Liu, Dongsheng Li

{"title":"DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation","authors":"Menglong Lu, Zhen Huang, Yunxiang Zhao, Zhiliang Tian, Yang Liu, Dongsheng Li","doi":"10.18653/v1/2023.acl-long.92","DOIUrl":"https://doi.org/10.18653/v1/2023.acl-long.92","url":null,"abstract":"Self-training emerges as an important research line on domain adaptation. By taking the model’s prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances in the target domain. However, the prediction errors of pseudo labels (label noise) challenge the performance of self-training. To address this problem, previous approaches only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. Although these strategies effectively reduce the label noise, they are prone to miss the hard examples. In this paper, we propose a new self-training framework for domain adaptation, namely Domain adversarial learning enhanced Self-Training Framework (DaMSTF). Firstly, DaMSTF involves meta-learning to estimate the importance of each pseudo instance, so as to simultaneously reduce the label noise and preserve hard examples. Secondly, we design a meta constructor for constructing the meta-validation set, which guarantees the effectiveness of the meta-learning module by improving the quality of the meta-validation set. Thirdly, we find that the meta-learning module suffers from the training guidance vanish- ment and tends to converge to an inferior optimal. To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal. Theoretically and experimentally, we demonstrate the effectiveness of the proposed DaMSTF. On the cross-domain sentiment classification task, DaMSTF improves the performance of BERT with an average of nearly 4%.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128372996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Reasoning in Large Language Models Through Symbolic Math Word Problems 通过符号数学单词问题在大型语言模型中的推理

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-08-03 DOI: 10.18653/v1/2023.findings-acl.364

Vedant Gaur, Nikunj Saunshi

{"title":"Reasoning in Large Language Models Through Symbolic Math Word Problems","authors":"Vedant Gaur, Nikunj Saunshi","doi":"10.18653/v1/2023.findings-acl.364","DOIUrl":"https://doi.org/10.18653/v1/2023.findings-acl.364","url":null,"abstract":"Large language models (LLMs) have revolutionized NLP by solving downstream tasks with little to no labeled data. Despite their versatile abilities, the larger question of their ability to reason remains ill-understood. This paper addresses reasoning in math word problems (MWPs) by studying symbolic versions of the numeric problems, since a symbolic expression is a\"concise explanation\"of the numeric answer. We create and use a symbolic version of the SVAMP dataset and find that GPT-3's davinci-002 model also has good zero-shot accuracy on symbolic MWPs. To evaluate the faithfulness of the model's reasoning, we go beyond accuracy and additionally evaluate the alignment between the final answer and the outputted reasoning, which correspond to numeric and symbolic answers respectively for MWPs. We explore a self-prompting approach to encourage the symbolic reasoning to align with the numeric answer, thus equipping the LLM with the ability to provide a concise and verifiable reasoning and making it more interpretable. Surprisingly, self-prompting also improves the symbolic accuracy to be higher than both the numeric and symbolic accuracies, thus providing an ensembling effect. The SVAMP_Sym dataset will be released for future research on symbolic math problems.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"24 25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128465904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

TREA: Tree-Structure Reasoning Schema for Conversational Recommendation 会话推荐的树状结构推理模式

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-20 DOI: 10.48550/arXiv.2307.10543

Wendi Li, Wei Wei, Xiaoye Qu, Xian-ling Mao, Ye Yuan, Wenfeng Xie, Dangyang Chen

引用次数: 2

Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models 性别调整:增强微调去偏见预训练语言模型

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-20 DOI: 10.48550/arXiv.2307.10522

Somayeh Ghanbarzadeh, Yan Huang, H. Palangi, R. C. Moreno, Hamed Khanpour

引用次数: 1

Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach 图神经网络的课程学习:基于多视角能力的方法

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-17 DOI: 10.48550/arXiv.2307.08859

Nidhi Vakil, Hadi Amiri

引用次数: 0

Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach 积极情绪激发促进多回合情绪支持对话:强化学习方法

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-16 DOI: 10.48550/arXiv.2307.07994

Jinfeng Zhou, Zhuang Chen, Bo Wang, Minlie Huang

引用次数: 1