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
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5635–5641
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.498
DOI:
10.18653/v1/2020.acl-main.498
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.498.pdf
Video:
 http://slideslive.com/38929337