Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity

Xinnuo Xu, Ondřej Dušek, Ioannis Konstas, Verena Rieser


Abstract
We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the dialogue context and the generated response, (2) we filter our training corpora based on the measure of coherence to obtain topically coherent and lexically diverse context-response pairs, (3) we then train a response generator using a conditional variational autoencoder model that incorporates the measure of coherence as a latent variable and uses a context gate to guarantee topical consistency with the context and promote lexical diversity. Experiments on the OpenSubtitles corpus show a substantial improvement over competitive neural models in terms of BLEU score as well as metrics of coherence and diversity.
Anthology ID:
D18-1432
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:
3981–3991
Language:
URL:
https://aclanthology.org/D18-1432
DOI:
10.18653/v1/D18-1432
Bibkey:
Cite (ACL):
Xinnuo Xu, Ondřej Dušek, Ioannis Konstas, and Verena Rieser. 2018. Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3981–3991, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity (Xu et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1432.pdf
Attachment:
 D18-1432.Attachment.pdf
Code
 XinnuoXu/CVAE_Dial
Data
OpenSubtitles