Question Answering for the Curated Web: Tasks and Methods in QA over Knowledge Bases and Text Collections
暫譯: 針對策劃網路的問答：知識庫與文本集合中的問答任務與方法
Rishiraj Saha Roy , Avishek Anand
- 出版商: Morgan & Claypool
- 出版日期: 2021-10-28
- 售價: $3,210
- 貴賓價: 9.5 折 $3,050
- 語言: 英文
- 頁數: 194
- 裝訂: Hardcover - also called cloth, retail trade, or trade
- ISBN: 1636392407
- ISBN-13: 9781636392400
海外代購書籍(需單獨結帳)
相關主題
商品描述
Question answering (QA) systems on the Web try to provide crisp answers to information needs posed in natural language, replacing the traditional ranked list of documents. QA, posing a multitude of research challenges, has emerged as one of the most actively investigated topics in information retrieval, natural language processing, and the artificial intelligence communities today. The flip side of such diverse and active interest is that publications are highly fragmented across several venues in the above communities, making it very difficult for new entrants to the field to get a good overview of the topic.
Through this book, we make an attempt towards mitigating the above problem by providing an overview of the state-of-the-art in question answering. We cover the twin paradigms of curated Web sources used in QA tasks ? trusted text collections like Wikipedia, and objective information distilled into large-scale knowledge bases. We discuss distinct methodologies that have been applied to solve the QA problem in both these paradigms, using instantiations of recent systems for illustration. We begin with an overview of the problem setup and evaluation, cover notable sub-topics like open-domain, multi-hop, and conversational QA in depth, and conclude with key insights and emerging topics. We believe that this resource is a valuable contribution towards a unified view on QA, helping graduate students and researchers planning to work on this topic in the near future.
商品描述(中文翻譯)
**網路上的問答系統（QA）試圖為以自然語言提出的信息需求提供簡潔的答案，取代傳統的文件排名列表**。問答系統面臨著眾多研究挑戰，已成為當前信息檢索、自然語言處理和人工智慧社群中最活躍的研究主題之一。這種多樣且活躍的興趣的另一面是，相關出版物在上述社群中高度分散，使得新進者很難對該主題有良好的概覽。
通過本書，我們試圖減輕上述問題，提供問答系統的最新技術概述。我們涵蓋了在問答任務中使用的兩種策展網路來源的範式——像維基百科這樣的可信文本集合，以及提煉成大型知識庫的客觀信息。我們討論了在這兩種範式中解決問答問題所應用的不同方法論，並使用近期系統的實例進行說明。我們首先概述問題設置和評估，深入探討開放領域、多跳和對話式問答等顯著子主題，最後總結關鍵見解和新興主題。我們相信，這本資源對於形成問答系統的統一視角是有價值的貢獻，幫助計劃在不久的將來從事該主題的研究生和研究人員。
作者簡介
Rishiraj Saha Roy is a Senior Researcher at the Max Planck In- stitute for Informatics (MPII), Saarbruecken, Germany. He leads the research group on Question Answering (https: //qa.mpi- inf.mpg.de), that focuses on robust and interpretable solutions for answering natural language questions over structured and unstructured data. He has about six years of research experience on question answering. In recent years, he has served on the PCs of conferences like SIGIR, CIKM, WSDM, AAAI, and EMNLP, and published at venues like SIGIR, CIKM, WSDM, WWW, and NAACL. Prior to joining MPII, he worked for one and a half years as a Computer Scientist at Adobe Research. He completed his PhD as a Microsoft Research India Fellow from the Indian Institute of Technology (IIT) Kharagpur.
Avishek Anand is an Assistant Professor at the Leibniz Univer- sity of Hannover, Germany, and a member of the L3S Research Center, Hannover. He has also been a visiting scholar at Ama- zon Search. His research aims to develop intelligent and trans- parent machine learning approaches to help humans find rele- vant information. Specifically, he is interested in scalable and in- terpretable representation learning methods for text and graphs for problems relating to the Web and information retrieval. He holds a PhD in Computer Science from the Max Planck Institute for Informatics (MPII), Saarbruecken, Germany. He has served in the PCs of numerous Web, IR, and NLP conferences and journals, like WSDM, SIGIR, ACL, TOIS, TKDE, and TWEB. He has served on the organizing committees of conferences like ICTIR, TPDL, Dagstuhl seminars and other summer schools. His research is sup- ported by generous grants from the German Science Foundation (DFG), EU Horizon 2020, Amazon research awards, and Schufa Holding AG.
作者簡介(中文翻譯)
Rishiraj Saha Roy 是德國薩爾布呂肯的邁斯普朗克資訊研究所 (Max Planck Institute for Informatics, MPII) 的高級研究員。他領導著一個專注於自然語言問題回答的研究小組 (https://qa.mpi-inf.mpg.de)，該小組致力於為結構化和非結構化數據提供穩健且可解釋的解決方案。他在問題回答方面擁有約六年的研究經驗。近年來，他曾擔任 SIGIR、CIKM、WSDM、AAAI 和 EMNLP 等會議的程序委員會成員，並在 SIGIR、CIKM、WSDM、WWW 和 NAACL 等會議上發表論文。在加入 MPII 之前，他在 Adobe Research 擔任計算機科學家，工作了一年半。他在印度理工學院 (IIT) 卡哈拉古爾獲得了微軟研究印度獎學金的博士學位。
Avishek Anand 是德國漢諾威的萊布尼茲大學 (Leibniz University of Hannover) 的助理教授，也是漢諾威 L3S 研究中心的成員。他曾在亞馬遜搜索擔任訪問學者。他的研究旨在開發智能且透明的機器學習方法，以幫助人類找到相關信息。具體而言，他對於可擴展且可解釋的文本和圖形表示學習方法感興趣，這些方法與網絡和信息檢索相關的問題有關。他擁有德國邁斯普朗克資訊研究所 (MPII) 的計算機科學博士學位。他曾在多個網絡、信息檢索 (IR) 和自然語言處理 (NLP) 會議和期刊的程序委員會中任職，如 WSDM、SIGIR、ACL、TOIS、TKDE 和 TWEB。他還曾在 ICTIR、TPDL、Dagstuhl 研討會和其他暑期學校的組織委員會中任職。他的研究得到了德國科學基金會 (DFG)、歐盟地平線 2020、亞馬遜研究獎和 Schufa Holding AG 的慷慨資助。
