Annual Meeting of the Association for Computational Linguistics最新文献_第2页

MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System 迈向可靠的多模态讽刺检测系统

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-14 DOI: 10.48550/arXiv.2307.07135

Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, Ruifeng Xu

引用次数: 0

Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section 充分利用有限的上下文长度:预测能力因临床笔记类型和笔记部分而异

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-13 DOI: 10.48550/arXiv.2307.07051

Hongyi Zheng, Yixin Zhu, L. Jiang, K. Cho, E. Oermann

引用次数: 0

Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models 自蒸馏量化:在基于变压器的语言模型中实现高压缩率

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-12 DOI: 10.48550/arXiv.2307.05972

James O'Neill, Sourav Dutta

引用次数: 0

ISLTranslate: Dataset for Translating Indian Sign Language ISLTranslate:印度手语翻译数据集

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-11 DOI: 10.48550/arXiv.2307.05440

Abhinav Joshi, Susmit Agrawal, Ashutosh Modi

引用次数: 0

Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features 赋能具有类型学特征的NLP模型的跨语言行为测试

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-11 DOI: 10.48550/arXiv.2307.05454

Ester Hlavnova, Sebastian Ruder

引用次数: 1

Learning to Generate Equitable Text in Dialogue from Biased Training Data 学习从有偏见的训练数据中生成公平的对话文本

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-10 DOI: 10.48550/arXiv.2307.04303

Anthony Sicilia, Malihe Alikhani

{"title":"Learning to Generate Equitable Text in Dialogue from Biased Training Data","authors":"Anthony Sicilia, Malihe Alikhani","doi":"10.48550/arXiv.2307.04303","DOIUrl":"https://doi.org/10.48550/arXiv.2307.04303","url":null,"abstract":"The ingrained principles of fairness in a dialogue system’s decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. Absence of equitable and inclusive principles can hinder the formation of common ground, which in turn negatively impacts the overall performance of the system. For example, misusing pronouns in a user interaction may cause ambiguity about the intended subject. Yet, there is no comprehensive study of equitable text generation in dialogue. Aptly, in this work, we use theories of computational learning to study this problem. We provide formal definitions of equity in text generation, and further, prove formal connections between learning human-likeness and learning equity: algorithms for improving equity ultimately reduce to algorithms for improving human-likeness (on augmented data). With this insight, we also formulate reasonable conditions under which text generation algorithms can learn to generate equitable text without any modifications to the biased training data on which they learn. To exemplify our theory in practice, we look at a group of algorithms for the GuessWhat?! visual dialogue game and, using this example, test our theory empirically. Our theory accurately predicts relative-performance of multiple algorithms in generating equitable text as measured by both human and automated evaluation.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131324223","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: 3

Answering Ambiguous Questions via Iterative Prompting 通过迭代提示回答模棱两可的问题

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-08 DOI: 10.48550/arXiv.2307.03897

Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Z. Ren

{"title":"Answering Ambiguous Questions via Iterative Prompting","authors":"Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Z. Ren","doi":"10.48550/arXiv.2307.03897","DOIUrl":"https://doi.org/10.48550/arXiv.2307.03897","url":null,"abstract":"In open-domain question answering, due to the ambiguity of questions, multiple plausible answers may exist.To provide feasible answers to an ambiguous question,one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity.An alternative is to gather candidate answers and aggregate them, but this method can be computationally costly and may neglect dependencies among answers.In this paper, we present AmbigPrompt to address the imperfections of existing approaches to answering ambiguous questions.Specifically, we integrate an answering model with a prompting model in an iterative manner.The prompting model adaptively tracks the reading process and progressively triggers the answering model to compose distinct and relevant answers. Additionally, we develop a task-specific post-pretraining approach for both the answering model and the prompting model, which greatly improves the performance of our framework. Empirical studies on two commonly-used open benchmarks show that AmbigPrompt achieves state-of-the-art or competitive results while using less memory and having a lower inference latency than competing approaches. Additionally, AmbigPrompt also performs well in low-resource settings.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115639598","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

Incomplete Utterance Rewriting as Sequential Greedy Tagging 序贯贪婪标记的不完全话语重写

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-08 DOI: 10.48550/arXiv.2307.06337

Yuxiang Chen

引用次数: 0

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation 重新审视跨语言摘要:基于语料库的研究和改进标注的新基准

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-08 DOI: 10.48550/arXiv.2307.04018

Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang

{"title":"Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation","authors":"Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang","doi":"10.48550/arXiv.2307.04018","DOIUrl":"https://doi.org/10.48550/arXiv.2307.04018","url":null,"abstract":"Most existing cross-lingual summarization (CLS) work constructs CLS corpora by simply and directly translating pre-annotated summaries from one language to another, which can contain errors from both summarization and translation processes.To address this issue, we propose ConvSumX, a cross-lingual conversation summarization benchmark, through a new annotation schema that explicitly considers source input context.ConvSumX consists of 2 sub-tasks under different real-world scenarios, with each covering 3 language directions.We conduct thorough analysis on ConvSumX and 3 widely-used manually annotated CLS corpora and empirically find that ConvSumX is more faithful towards input text.Additionally, based on the same intuition, we propose a 2-Step method, which takes both conversation and summary as input to simulate human annotation process.Experimental results show that 2-Step method surpasses strong baselines on ConvSumX under both automatic and human evaluation.Analysis shows that both source input text and summary are crucial for modeling cross-lingual summaries.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128404172","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

Improving Automatic Quotation Attribution in Literary Novels 改进文学小说引文自动归因

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-07 DOI: 10.48550/arXiv.2307.03734

Krishnapriya Vishnubhotla, Frank Rudzicz, Graeme Hirst, Adam Hammond

引用次数: 0