Enhanced Simple Question Answering with Contrastive Learning
Paper
Paper/Presentation Title | Enhanced Simple Question Answering with Contrastive Learning |
---|---|
Presentation Type | Paper |
Authors | Wang, Xin, Yang, Lan, He, Honglian, Fang, Yu, Zhan, Huayi and Zhang, Ji |
Journal or Proceedings Title | Proceedings of the 15th International Conference on Knowledge Science, Engineering and Management (KSEM 2022) |
Journal Citation | 13368, pp. 502-515 |
Number of Pages | 14 |
Year | 2022 |
Publisher | Springer |
Place of Publication | Switzerland |
ISBN | 9783031109829 |
9783031109836 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-10983-6_39 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-031-10983-6_39 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-031-10983-6 |
Conference/Event | 15th International Conference on Knowledge Science, Engineering and Management (KSEM 2022) |
Event Details | 15th International Conference on Knowledge Science, Engineering and Management (KSEM 2022) Parent International Conference on Knowledge Science, Engineering and Management Delivery In person Event Date 06 to end of 08 Aug 2022 Event Location Singapore |
Abstract | Answer natural language questions on knowledge bases (KBQA) has attracted wide attention. Several techniques have been developed for answering simple questions. These techniques mostly rely on deep networks to perform classification for relation prediction. Nowadays, contrastive learning has shown its powers in improving performances of classification, while most prior techniques do not gain benefit from this. In light of these, we propose a novel approach to answering simple questions on knowledge bases. Our approach has two key features. (1) It leverages pre-trained transformers to gain better performance on entity linking. (2) It employs a contrastive learning based model for relation prediction. We experimentally verify the performance of our approach, and show that our approach achieves an accuracy of 83.54%, which beats existing state-of-the-art techniques, on a typical benchmark dataset; we also conduct a deep analysis to show advantages of our technique, especially its sub-modules. |
Keywords | Knowledge base; Question answering; Contrastive learning; Transfer learning; Pre-trained model |
ANZSRC Field of Research 2020 | 461299. Software engineering not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Series | Lecture Notes in Computer Science |
Byline Affiliations | Southwest Petroleum University, China |
Sichuan Changhong Electric, China | |
University of Southern Queensland |
https://research.usq.edu.au/item/z58zz/enhanced-simple-question-answering-with-contrastive-learning
111
total views1
total downloads5
views this month0
downloads this month