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.
@article{arxiv.1909.09696,
title = {A Gated Self-attention Memory Network for Answer Selection},
author = {Tuan Lai and Quan Hung Tran and Trung Bui and Daisuke Kihara},
journal= {arXiv preprint arXiv:1909.09696},
year = {2019}
}
Comments
Accepted at the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019)