DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seonwoo, Yeon | ko |
dc.contributor.author | Son, Juhee | ko |
dc.contributor.author | Jin, Jiho | ko |
dc.contributor.author | Lee, Sang-Woo | ko |
dc.contributor.author | Kim, Ji-Hoon | ko |
dc.contributor.author | Ha, Jung-Woo | ko |
dc.contributor.author | Oh, Alice Haeyun | ko |
dc.date.accessioned | 2022-11-09T13:01:25Z | - |
dc.date.available | 2022-11-09T13:01:25Z | - |
dc.date.created | 2022-06-13 | - |
dc.date.issued | 2022-05-24 | - |
dc.identifier.citation | 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, pp.1487 - 1492 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299441 | - |
dc.description.abstract | The 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.language | English | - |
dc.publisher | Association for Computational Linguistics | - |
dc.title | Two-Step Question Retrieval for Open-Domain QA | - |
dc.type | Conference | - |
dc.identifier.wosid | 000828767401042 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1487 | - |
dc.citation.endingpage | 1492 | - |
dc.citation.publicationname | 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 | - |
dc.identifier.conferencecountry | IE | - |
dc.identifier.conferencelocation | Dublin | - |
dc.contributor.localauthor | Oh, Alice Haeyun | - |
dc.contributor.nonIdAuthor | Son, Juhee | - |
dc.contributor.nonIdAuthor | Jin, Jiho | - |
dc.contributor.nonIdAuthor | Lee, Sang-Woo | - |
dc.contributor.nonIdAuthor | Kim, Ji-Hoon | - |
dc.contributor.nonIdAuthor | Ha, Jung-Woo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.