Deep Learning for Dialogue Systems: Chit-Chat and Beyond

IF 8.3 2区计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS

Foundations and Trends in Information Retrieval Pub Date : 2022-01-01 DOI:10.1561/1500000083

Rui Yan, Juntao Li, Zhou Yu

{"title":"Deep Learning for Dialogue Systems: Chit-Chat and Beyond","authors":"Rui Yan, Juntao Li, Zhou Yu","doi":"10.1561/1500000083","DOIUrl":null,"url":null,"abstract":"Recommendation, information retrieval, and other information access systems pose unique challenges for investigating and applying the fairness and non-discrimination concepts that have been developed for studying other machine learning systems. While fair information access shares many commonalities with fair classification, there are important differences: the multistakeholder nature of information access applications, the rank-based problem setting, the centrality of personalization in many cases, and the role of user response all complicate the problem of identifying precisely what types and operationalizations of fairness may be relevant. In this monograph, we present a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic. We Michael D. Ekstrand, Anubrata Das, Robin Burke and Fernando Diaz (2022), “Fairness in Information Access Systems”, Foundations and Trends® in Information Retrieval: Vol. 16, No. 1-2, pp 1–177. DOI: 10.1561/1500000079. ©2022 M. D. Ekstrand et al. Full text available at: http://dx.doi.org/10.1561/1500000079","PeriodicalId":48829,"journal":{"name":"Foundations and Trends in Information Retrieval","volume":"19 1","pages":"417-589"},"PeriodicalIF":8.3000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Foundations and Trends in Information Retrieval","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1561/1500000083","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 10

Abstract

Recommendation, information retrieval, and other information access systems pose unique challenges for investigating and applying the fairness and non-discrimination concepts that have been developed for studying other machine learning systems. While fair information access shares many commonalities with fair classification, there are important differences: the multistakeholder nature of information access applications, the rank-based problem setting, the centrality of personalization in many cases, and the role of user response all complicate the problem of identifying precisely what types and operationalizations of fairness may be relevant. In this monograph, we present a taxonomy of the various dimensions of fair information access and survey the literature to date on this new and rapidly-growing topic. We Michael D. Ekstrand, Anubrata Das, Robin Burke and Fernando Diaz (2022), “Fairness in Information Access Systems”, Foundations and Trends® in Information Retrieval: Vol. 16, No. 1-2, pp 1–177. DOI: 10.1561/1500000079. ©2022 M. D. Ekstrand et al. Full text available at: http://dx.doi.org/10.1561/1500000079

查看原文本刊更多论文

对话系统的深度学习:闲聊和超越

推荐、信息检索和其他信息访问系统对调查和应用公平和非歧视概念提出了独特的挑战，这些概念已经为研究其他机器学习系统而开发。虽然公平的信息访问与公平的分类有许多共同点，但也有重要的区别:信息访问应用的多利益相关者性质、基于排名的问题设置、在许多情况下个性化的中心地位以及用户响应的作用，所有这些都使准确识别公平的类型和操作可能相关的问题复杂化。在这本专著中，我们提出了公平信息获取的各个维度的分类，并调查了迄今为止关于这个新的和快速增长的主题的文献。我们Michael D. Ekstrand, Anubrata Das, Robin Burke和Fernando Diaz(2022)，“信息获取系统的公平性”，《信息检索的基础与趋势》，第16卷第1-2期，第1-177页。DOI: 10.1561 / 1500000079。©2022 M. D. Ekstrand等。全文可在:http://dx.doi.org/10.1561/1500000079

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Foundations and Trends in Information Retrieval COMPUTER SCIENCE, INFORMATION SYSTEMS-

CiteScore

39.10

自引率

0.00%

发文量

期刊介绍： The surge in research across all domains in the past decade has resulted in a plethora of new publications, causing an exponential growth in published research. Navigating through this extensive literature and staying current has become a time-consuming challenge. While electronic publishing provides instant access to more articles than ever, discerning the essential ones for a comprehensive understanding of any topic remains an issue. To tackle this, Foundations and Trends® in Information Retrieval - FnTIR - addresses the problem by publishing high-quality survey and tutorial monographs in the field. Each issue of Foundations and Trends® in Information Retrieval - FnT IR features a 50-100 page monograph authored by research leaders, covering tutorial subjects, research retrospectives, and survey papers that provide state-of-the-art reviews within the scope of the journal.