Please use this identifier to cite or link to this item: http://dx.doi.org/10.25673/38192
Title: Answering comparative questions with arguments
Author(s): Bondarenko, AlexanderLook up in the Integrated Authority File of the German National Library
Panchenko, Alexander
Beloucif, Meriem
Biemann, ChrisLook up in the Integrated Authority File of the German National Library
Hagen, MatthiasLook up in the Integrated Authority File of the German National Library
Issue Date: 2020
Type: Article
Language: English
Abstract: Question answering platforms such as Yahoo! Answers or Quora always contained questions that ask other humans for help when comparing two or more options. Since nowadays more and more people also “talk” to their devices, such comparative questions are also part of the query stream that major search engines receive. Interestingly, major search engines answer some comparative questions pretty well while for others, they just show the “standard” ten blue links. But a good response to a comparative question might be very different from these ten blue links—for example, a direct answer could show an aggregation of the pros and cons of the different options. This observation motivated our DFG-funded project “ACQuA: Answering Comparative Questions with Arguments” for which we describe the achieved results so far, and ongoing activities like the first shared task on argument retrieval.
URI: https://opendata.uni-halle.de//handle/1981185920/38435
http://dx.doi.org/10.25673/38192
Open Access: Open access publication
License: (CC BY 4.0) Creative Commons Attribution 4.0(CC BY 4.0) Creative Commons Attribution 4.0
Sponsor/Funder: Publikationsfond MLU
Journal Title: Datenbank-Spektrum
Publisher: Springer
Publisher Place: Berlin
Volume: 20
Issue: 2
Original Publication: 10.1007/s13222-020-00346-8
Page Start: 155
Page End: 160
Appears in Collections:Open Access Publikationen der MLU

Files in This Item:
File Description SizeFormat 
Bondarenko2020_Article_AnsweringComparativeQuestionsW.pdf1.7 MBAdobe PDFThumbnail
View/Open