Knowledge-Enhanced Evidence Retrieval for Counterargument Generation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 90
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorJo, Yohanko
dc.contributor.authorYoo, Haneulko
dc.contributor.authorHovy, Eduardko
dc.contributor.author오혜연ko
dc.contributor.authorReed, Chrisko
dc.contributor.authorBak, JinYeongko
dc.date.accessioned2021-11-09T06:46:05Z-
dc.date.available2021-11-09T06:46:05Z-
dc.date.created2021-11-02-
dc.date.created2021-11-02-
dc.date.issued2021-11-
dc.identifier.citationThe 2021 Conference on Empirical Methods in Natural Language Processing-
dc.identifier.urihttp://hdl.handle.net/10203/289004-
dc.description.abstractFinding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.-
dc.languageEnglish-
dc.publisherEmpirical Methods in Natural Language Processing (EMNLP 2021, Findings)-
dc.titleKnowledge-Enhanced Evidence Retrieval for Counterargument Generation-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationnameThe 2021 Conference on Empirical Methods in Natural Language Processing-
dc.identifier.conferencecountryDR-
dc.identifier.conferencelocationOnline & Barcelo Bavaro Convention Centre, Punta Cana-
dc.contributor.localauthor오혜연-
dc.contributor.nonIdAuthorJo, Yohan-
dc.contributor.nonIdAuthorYoo, Haneul-
dc.contributor.nonIdAuthorHovy, Eduard-
dc.contributor.nonIdAuthorReed, Chris-
dc.contributor.nonIdAuthorBak, JinYeong-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0