Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation
This work addresses the challenge of creating more human-like conversational agents by improving emotional response generation, though it is incremental as it builds on existing neural approaches.
The paper tackles the problem of generating emotional responses in dialogue systems by proposing a two-stage agent that first creates a semantically appropriate prototype and then refines it for emotion, outperforming existing models on emotion generation while preserving semantics in evaluations.
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and semantics, and requires rare emotion-annotated large-scale dialogue corpus. Inspired by the "think twice" behavior in human dialogue, we propose a two-stage conversational agent for the generation of emotional dialogue. Firstly, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics. Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis. Experimental results on the DailyDialog and EmpatheticDialogues datasets demonstrate that the proposed conversational outperforms the comparison models in emotion generation and maintains the semantic performance in automatic and human evaluations.