Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Ashutosh Baheti, Alan Ritter, Jiwei Li, Bill Dolan


Abstract
Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this challenge, we propose a simple yet effective approach for incorporating side information in the form of distributional constraints over the generated responses. We propose two constraints that help generate more content rich responses that are based on a model of syntax and topics (Griffiths et al., 2005) and semantic similarity (Arora et al., 2016). We evaluate our approach against a variety of competitive baselines, using both automatic metrics and human judgments, showing that our proposed approach generates responses that are much less generic without sacrificing plausibility. A working demo of our code can be found at https://github.com/abaheti95/DC-NeuralConversation.
Anthology ID:
D18-1431
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3970–3980
Language:
URL:
https://aclanthology.org/D18-1431
DOI:
10.18653/v1/D18-1431
Bibkey:
Cite (ACL):
Ashutosh Baheti, Alan Ritter, Jiwei Li, and Bill Dolan. 2018. Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3970–3980, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints (Baheti et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1431.pdf
Code
 abaheti95/DC-NeuralConversation +  additional community code