Crossing Variational Autoencoders for Answer Retrieval

Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang


Abstract
Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semantics between question and answer. In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions. Experiments show that our method outperforms the state-of-the-art answer retrieval method on SQuAD.
Anthology ID:
2020.acl-main.498
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5635–5641
Language:
URL:
https://aclanthology.org/2020.acl-main.498
DOI:
10.18653/v1/2020.acl-main.498
Bibkey:
Cite (ACL):
Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, and Meng Jiang. 2020. Crossing Variational Autoencoders for Answer Retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5635–5641, Online. Association for Computational Linguistics.
Cite (Informal):
Crossing Variational Autoencoders for Answer Retrieval (Yu et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.498.pdf
Video:
 http://slideslive.com/38929337
Data
SQuAD