Pattern-revising Enhanced Simple Question Answering over Knowledge Bases

Yanchao Hao, Hao Liu, Shizhu He, Kang Liu, Jun Zhao


Abstract
Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks. Simple questions constitute a large part of questions queried on the web, still being a challenge to QA systems. In this work, we propose to conduct pattern extraction and entity linking first, and put forward pattern revising procedure to mitigate the error propagation problem. In order to learn to rank candidate subject-predicate pairs to enable the relevant facts retrieval given a question, we propose to do joint fact selection enhanced by relation detection. Multi-level encodings and multi-dimension information are leveraged to strengthen the whole procedure. The experimental results demonstrate that our approach sets a new record in this task, outperforming the current state-of-the-art by an absolute large margin.
Anthology ID:
C18-1277
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3272–3282
Language:
URL:
https://aclanthology.org/C18-1277
DOI:
Bibkey:
Cite (ACL):
Yanchao Hao, Hao Liu, Shizhu He, Kang Liu, and Jun Zhao. 2018. Pattern-revising Enhanced Simple Question Answering over Knowledge Bases. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3272–3282, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Pattern-revising Enhanced Simple Question Answering over Knowledge Bases (Hao et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/C18-1277.pdf
Data
SimpleQuestions