Abstract
Question answering over knowledge bases (KBQA) usually involves three sub-tasks, namely topic entity detection, entity linking and relation detection. Due to the large number of entities and relations inside knowledge bases (KB), previous work usually utilized sophisticated rules to narrow down the search space and managed only a subset of KBs in memory. In this work, we leverage a retrieve-and-rerank framework to access KBs via traditional information retrieval (IR) method, and re-rank retrieved candidates with more powerful neural networks such as the pre-trained BERT model. Considering the fact that directly assigning a different BERT model for each sub-task may incur prohibitive costs, we propose to share a BERT encoder across all three sub-tasks and define task-specific layers on top of the shared layer. The unified model is then trained under a multi-task learning framework. Experiments show that: (1) Our IR-based retrieval method is able to collect high-quality candidates efficiently, thus enables our method adapt to large-scale KBs easily; (2) the BERT model improves the accuracy across all three sub-tasks; and (3) benefiting from multi-task learning, the unified model obtains further improvements with only 1/3 of the original parameters. Our final model achieves competitive results on the SimpleQuestions dataset and superior performance on the FreebaseQA dataset.- Anthology ID:
- 2021.eacl-main.26
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 347–357
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.26
- DOI:
- 10.18653/v1/2021.eacl-main.26
- Cite (ACL):
- Zhiguo Wang, Patrick Ng, Ramesh Nallapati, and Bing Xiang. 2021. Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 347–357, Online. Association for Computational Linguistics.
- Cite (Informal):
- Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering (Wang et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.26.pdf
- Data
- SimpleQuestions