Kun Qian, Marina Danilevsky, Yannis Katsis, B. Kawas, Erick Oduor, Lucian Popa, Yunyao Li
{"title":"XNLP: A Living Survey for XAI Research in Natural Language Processing","authors":"Kun Qian, Marina Danilevsky, Yannis Katsis, B. Kawas, Erick Oduor, Lucian Popa, Yunyao Li","doi":"10.1145/3397482.3450728","DOIUrl":null,"url":null,"abstract":"We present XNLP: an interactive browser-based system embodying a living survey of recent state-of-the-art research in the field of Explainable AI (XAI) within the domain of Natural Language Processing (NLP). The system visually organizes and illustrates XAI-NLP publications and distills their content to allow users to gain insights, generate ideas, and explore the field. We hope that XNLP can become a leading demonstrative example of a living survey, balancing the depth and quality of a traditional well-constructed survey paper with the collaborative dynamism of a widely available interactive tool. XNLP can be accessed at: https://xainlp2020.github.io/xainlp.","PeriodicalId":216190,"journal":{"name":"26th International Conference on Intelligent User Interfaces - Companion","volume":"6 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"26th International Conference on Intelligent User Interfaces - Companion","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3397482.3450728","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 15
Abstract
We present XNLP: an interactive browser-based system embodying a living survey of recent state-of-the-art research in the field of Explainable AI (XAI) within the domain of Natural Language Processing (NLP). The system visually organizes and illustrates XAI-NLP publications and distills their content to allow users to gain insights, generate ideas, and explore the field. We hope that XNLP can become a leading demonstrative example of a living survey, balancing the depth and quality of a traditional well-constructed survey paper with the collaborative dynamism of a widely available interactive tool. XNLP can be accessed at: https://xainlp2020.github.io/xainlp.