Retrieve and Re-rank: A Simple and Effective IR Approach to Simple Question Answering over Knowledge Graphs

Vishal Gupta, Manoj Chinnakotla, Manish Shrivastava


Abstract
SimpleQuestions is a commonly used benchmark for single-factoid question answering (QA) over Knowledge Graphs (KG). Existing QA systems rely on various components to solve different sub-tasks of the problem (such as entity detection, entity linking, relation prediction and evidence integration). In this work, we propose a different approach to the problem and present an information retrieval style solution for it. We adopt a two-phase approach: candidate generation and candidate re-ranking to answer questions. We propose a Triplet-Siamese-Hybrid CNN (TSHCNN) to re-rank candidate answers. Our approach achieves an accuracy of 80% which sets a new state-of-the-art on the SimpleQuestions dataset.
Anthology ID:
W18-5504
Volume:
Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venues:
EMNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–27
Language:
URL:
https://aclanthology.org/W18-5504
DOI:
10.18653/v1/W18-5504
Bibkey:
Cite (ACL):
Vishal Gupta, Manoj Chinnakotla, and Manish Shrivastava. 2018. Retrieve and Re-rank: A Simple and Effective IR Approach to Simple Question Answering over Knowledge Graphs. In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), pages 22–27, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Retrieve and Re-rank: A Simple and Effective IR Approach to Simple Question Answering over Knowledge Graphs (Gupta et al., 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/W18-5504.pdf
Data
SimpleQuestions