Better conversations by modeling, filtering, and optimizing for coherence and diversity

Xu Xinnuo, Ondrej Dusek, Ioannis Konstas, Verena Rieser

Research output: Chapter in Book/Report/Conference proceedingConference contribution

50 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics
Pages3981–3991
Number of pages11
ISBN (Electronic)9781948087841
Publication statusPublished - 31 Oct 2018
Event2018 Conference on Empirical Methods in Natural Language Processing - Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2018
Country/TerritoryBelgium
CityBrussels
Period31/10/184/11/18

Fingerprint

Dive into the research topics of 'Better conversations by modeling, filtering, and optimizing for coherence and diversity'. Together they form a unique fingerprint.

Cite this