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

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.

References in corpus (12)

• A Neural Conversational Model
• Topic Aware Neural Response Generation
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Neural Responding Machine for Short-Text Conversation
• Adversarial Learning for Neural Dialogue Generation
• Toward Controlled Generation of Text
• Learning to Decode for Future Success
• Improving Variational Encoder-Decoders in Dialogue Generation
• Latent Variable Dialogue Models and their Diversity
• A Conditional Variational Framework for Dialog Generation
• Steering Output Style and Topic in Neural Response Generation
• Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation