Two-Step Question Retrieval for Open-Domain QA

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 81
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorSeonwoo, Yeonko
dc.contributor.authorSon, Juheeko
dc.contributor.authorJin, Jihoko
dc.contributor.authorLee, Sang-Wooko
dc.contributor.authorKim, Ji-Hoonko
dc.contributor.authorHa, Jung-Wooko
dc.contributor.authorOh, Alice Haeyunko
dc.date.accessioned2022-11-09T13:01:25Z-
dc.date.available2022-11-09T13:01:25Z-
dc.date.created2022-06-13-
dc.date.issued2022-05-24-
dc.identifier.citation60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, pp.1487 - 1492-
dc.identifier.urihttp://hdl.handle.net/10203/299441-
dc.description.abstractThe retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential QuestionIndexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.-
dc.languageEnglish-
dc.publisherAssociation for Computational Linguistics-
dc.titleTwo-Step Question Retrieval for Open-Domain QA-
dc.typeConference-
dc.identifier.wosid000828767401042-
dc.type.rimsCONF-
dc.citation.beginningpage1487-
dc.citation.endingpage1492-
dc.citation.publicationname60th Annual Meeting of the Association for Computational Linguistics, ACL 2022-
dc.identifier.conferencecountryIE-
dc.identifier.conferencelocationDublin-
dc.contributor.localauthorOh, Alice Haeyun-
dc.contributor.nonIdAuthorSon, Juhee-
dc.contributor.nonIdAuthorJin, Jiho-
dc.contributor.nonIdAuthorLee, Sang-Woo-
dc.contributor.nonIdAuthorKim, Ji-Hoon-
dc.contributor.nonIdAuthorHa, Jung-Woo-
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