Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

TL;DR

This paper introduces the Emotional Chatting Machine (ECM), a novel large-scale conversational model that generates emotionally appropriate responses by modeling internal and external emotional states.

Contribution

It is the first to incorporate emotion modeling in large-scale conversation generation using internal and external memory mechanisms.

Findings

ECM produces responses that are both content-relevant and emotionally consistent.

The model effectively captures internal emotion dynamics.

External emotion vocabulary enhances emotional expression accuracy.

Abstract

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose Emotional Chatting Machine (ECM) that can generate appropriate responses not only in content (relevant and grammatical) but also in emotion (emotionally consistent). To the best of our knowledge, this is the first work that addresses the emotion factor in large-scale conversation generation. ECM addresses the factor using three new mechanisms that respectively (1) models the high-level abstraction of emotion expressions by embedding emotion categories, (2) captures the change of implicit internal emotion states, and (3) uses explicit emotion expressions with an external emotion vocabulary. Experiments show that the proposed model can generate responses appropriate not only in content but also in emotion.