Exemplar Encoder-Decoder for Neural Conversation Generation

Gaurav Pandey, Danish Contractor, Vineet Kumar, Sachindra Joshi


Abstract
In this paper we present the Exemplar Encoder-Decoder network (EED), a novel conversation model that learns to utilize similar examples from training data to generate responses. Similar conversation examples (context-response pairs) from training data are retrieved using a traditional TF-IDF based retrieval model and the corresponding responses are used by our decoder to generate the ground truth response. The contribution of each retrieved response is weighed by the similarity of corresponding context with the input context. As a result, our model learns to assign higher similarity scores to those retrieved contexts whose responses are crucial for generating the final response. We present detailed experiments on two large data sets and we find that our method out-performs state of the art sequence to sequence generative models on several recently proposed evaluation metrics.
Anthology ID:
P18-1123
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1329–1338
Language:
URL:
https://aclanthology.org/P18-1123
DOI:
10.18653/v1/P18-1123
Bibkey:
Cite (ACL):
Gaurav Pandey, Danish Contractor, Vineet Kumar, and Sachindra Joshi. 2018. Exemplar Encoder-Decoder for Neural Conversation Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1329–1338, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Exemplar Encoder-Decoder for Neural Conversation Generation (Pandey et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1123.pdf
Presentation:
 P18-1123.Presentation.pdf
Video:
 https://aclanthology.org/P18-1123.mp4