Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies最新文献

筛选

英文中文

Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation Active2学习:主动减少序列标注和机器翻译学习的主动学习方法中的冗余:主动减少序列标注和机器翻译的主动学习方法中的冗余

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Pub Date : 2021-03-11 DOI: 10.18653/V1/2021.NAACL-MAIN.159

Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati

{"title":"Active2 Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation","authors":"Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati","doi":"10.18653/V1/2021.NAACL-MAIN.159","DOIUrl":"https://doi.org/10.18653/V1/2021.NAACL-MAIN.159","url":null,"abstract":"While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and time-consuming. Active Learning (AL) strategies reduce the need for huge volumes of labeled data by iteratively selecting a small number of examples for manual annotation based on their estimated utility in training the given model. In this paper, we argue that since AL strategies choose examples independently, they may potentially select similar examples, all of which may not contribute significantly to the learning process. Our proposed approach, Activemathbf{^2} Learning (Amathbf{^2}L), actively adapts to the deep learning model being trained to eliminate such redundant examples chosen by an AL strategy. We show that Amathbf{^2}L is widely applicable by using it in conjunction with several different AL strategies and NLP tasks. We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by ≈ mathbf{3-25%} on an absolute scale on multiple NLP tasks while achieving the same performance with virtually no additional computation overhead.","PeriodicalId":251110,"journal":{"name":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"04 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127178970","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: 6

Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models 文本模块化网络:学习用现有模型的语言分解任务

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Pub Date : 1900-01-01 DOI: 10.18653/V1/2021.NAACL-MAIN.99

Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, Ashish Sabharwal

{"title":"Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models","authors":"Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, Ashish Sabharwal","doi":"10.18653/V1/2021.NAACL-MAIN.99","DOIUrl":"https://doi.org/10.18653/V1/2021.NAACL-MAIN.99","url":null,"abstract":"We propose a general framework called Text Modular Networks(TMNs) for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. To ensure solvability of simpler tasks, TMNs learn the textual input-output behavior (i.e., language) of existing models through their datasets. This differs from prior decomposition-based approaches which, besides being designed specifically for each complex task, produce decompositions independent of existing sub-models. Specifically, we focus on Question Answering (QA) and show how to train a next-question generator to sequentially produce sub-questions targeting appropriate sub-models, without additional human annotation. These sub-questions and answers provide a faithful natural language explanation of the model’s reasoning. We use this framework to build ModularQA, a system that can answer multi-hop reasoning questions by decomposing them into sub-questions answerable by a neural factoid single-span QA model and a symbolic calculator. Our experiments show that ModularQA is more versatile than existing explainable systems for DROP and HotpotQA datasets, is more robust than state-of-the-art blackbox (uninterpretable) systems, and generates more understandable and trustworthy explanations compared to prior work.","PeriodicalId":251110,"journal":{"name":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116499146","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: 70