Publications
Detailed Information
Case-Based Reasoning for Natural Language Queries over Knowledge Bases
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Das, Rajarshi | - |
dc.contributor.author | Zaheer, Manzil | - |
dc.contributor.author | Thai, Dung | - |
dc.contributor.author | Godbole, Ameya | - |
dc.contributor.author | Perez, Ethan | - |
dc.contributor.author | Lee, Jay-Yoon | - |
dc.contributor.author | Tan, Lizhen | - |
dc.contributor.author | Polymenakos, Lazaros | - |
dc.contributor.author | McCallum, Andrew | - |
dc.date.accessioned | 2024-05-03T07:38:33Z | - |
dc.date.available | 2024-05-03T07:38:33Z | - |
dc.date.created | 2024-04-11 | - |
dc.date.issued | 2021-11 | - |
dc.identifier.citation | 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), pp.9594-9611 | - |
dc.identifier.uri | https://hdl.handle.net/10371/200917 | - |
dc.description.abstract | It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions - a paradigm known as case-based reasoning (CBR). We propose a neuro-symbolic CBR approach (CBR-KBQA) for question answering over large knowledge bases. CBR-KBQA consists of a nonparametric memory that stores cases (question and logical forms) and a parametric model that can generate a logical form for a new question by retrieving cases that are relevant to it. On several KBQA datasets that contain complex questions, CBR-KBQA achieves competitive performance. For example, on the COMPLEXWEBQUESTIONS dataset, CBR-KBQA outperforms the current state of the art by 11% on accuracy. Furthermore, we show that CBR-KBQA is capable of using new cases without any further training: by incorporating a few human-labeled examples in the case memory, CBR-KBQA is able to successfully generate logical forms containing unseen KB entities as well as relations. | - |
dc.language | 영어 | - |
dc.publisher | ASSOC COMPUTATIONAL LINGUISTICS-ACL | - |
dc.title | Case-Based Reasoning for Natural Language Queries over Knowledge Bases | - |
dc.type | Article | - |
dc.identifier.doi | 10.18653/v1/2021.emnlp-main.755 | - |
dc.citation.journaltitle | 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021) | - |
dc.identifier.wosid | 000860727003056 | - |
dc.identifier.scopusid | 2-s2.0-85121717169 | - |
dc.citation.endpage | 9611 | - |
dc.citation.startpage | 9594 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Lee, Jay-Yoon | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.