A Gated Self-attention Memory Network for Answer Selection

Tuan Lai, Quan Hung Tran, Trung Bui, Daisuke Kihara

[How to correct problems with metadata yourself]

Abstract
Answer selection is an important research problem, with applications in many areas. Previous deep learning based approaches for the task mainly adopt the Compare-Aggregate architecture that performs word-level comparison followed by aggregation. In this work, we take a departure from the popular Compare-Aggregate architecture, and instead, propose a new gated self-attention memory network for the task. Combined with a simple transfer learning technique from a large-scale online corpus, our model outperforms previous methods by a large margin, achieving new state-of-the-art results on two standard answer selection datasets: TrecQA and WikiQA.
Anthology ID:
D19-1610
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5953–5959
Language:
URL:
https://aclanthology.org/D19-1610
DOI:
10.18653/v1/D19-1610
Bibkey:
Cite (ACL):
Tuan Lai, Quan Hung Tran, Trung Bui, and Daisuke Kihara. 2019. A Gated Self-attention Memory Network for Answer Selection. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5953–5959, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
A Gated Self-attention Memory Network for Answer Selection (Lai et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D19-1610.pdf
Code
 laituan245/StackExchangeQA
Data
WikiQA
PDF Search Code