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

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

1 Oct 2018EMNLP 2018 10archive 2025-07-28

Xinnuo Xu, Ond{\v{r}}ej Du{\v{s}}ek, Ioannis Konstas, Verena Rieser

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.

PaperPDFCode

Code

XinnuoXu/CVAE_Dial officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderDialogue GenerationDiversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GloVe

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections