MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation

Meng Zou, Xihan Li, Haokun Liu, Zhihong Deng


Abstract
Neural encoder-decoder models have been widely applied to conversational response generation, which is a research hot spot in recent years. However, conventional neural encoder-decoder models tend to generate commonplace responses like “I don’t know” regardless of what the input is. In this paper, we analyze this problem from a new perspective: latent vectors. Based on it, we propose an easy-to-extend learning framework named MEMD (Multi-Encoder to Multi-Decoder), in which an auxiliary encoder and an auxiliary decoder are introduced to provide necessary training guidance without resorting to extra data or complicating network’s inner structure. Experimental results demonstrate that our method effectively improve the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies.
Anthology ID:
C18-1109
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1281–1291
Language:
URL:
https://aclanthology.org/C18-1109
DOI:
Bibkey:
Cite (ACL):
Meng Zou, Xihan Li, Haokun Liu, and Zhihong Deng. 2018. MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1281–1291, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation (Zou et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1109.pdf