Polite Dialogue Generation Without Parallel Data

Understand

Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate.

• Moreover, parallel datasets for regular-to-stylistic pairs are usually unavailable.
• We present three weakly-supervised models that can generate diverse polite (or rude) dialogue responses without parallel data.
• Our late fusion model (Fusion) merges the decoder of an encoder-attention-decoder dialogue model with a language model trained on stand-alone polite utterances.