Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
This work addresses the challenge of producing more natural and engaging conversations in AI chatbots, though it is incremental as it builds on existing encoder-decoder models.
The researchers tackled the problem of improving open-domain conversational agents by enhancing coherence and diversity in generated responses, achieving substantial improvements in BLEU score and coherence/diversity metrics on the OpenSubtitles corpus.
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.