Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, Shuming Shi


Abstract
Traditional generative dialogue models generate responses solely from input queries. Such information is insufficient for generating a specific response since a certain query could be answered in multiple ways. Recently, researchers have attempted to fill the information gap by exploiting information retrieval techniques. For a given query, similar dialogues are retrieved from the entire training data and considered as an additional knowledge source. While the use of retrieval may harvest extensive information, the generative models could be overwhelmed, leading to unsatisfactory performance. In this paper, we propose a new framework which exploits retrieval results via a skeleton-to-response paradigm. At first, a skeleton is extracted from the retrieved dialogues. Then, both the generated skeleton and the original query are used for response generation via a novel response generator. Experimental results show that our approach significantly improves the informativeness of the generated responses
Anthology ID:
N19-1124
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1219–1228
Language:
URL:
https://aclanthology.org/N19-1124
DOI:
10.18653/v1/N19-1124
Bibkey:
Cite (ACL):
Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Wai Lam, and Shuming Shi. 2019. Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1219–1228, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory (Cai et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1124.pdf
Code
 jcyk/skeleton-to-response