An Iterative Associative Memory Model for Empathetic Response Generation

arXiv:2402.17959v1 Announce Type: new
Abstract: Empathetic response generation is to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates iteratively capturing and understanding associated words across dialogue utterances. However, existing approaches regard dialogue utterances as either a long sequence or independent utterances for comprehension, which are prone to overlook the associated words between them. To address this issue, we propose an Iterative Associative Memory Model (IAMM) …

abstract arxiv cognitive cs.cl cs.hc dialogue generate iterative memory posit regard responses type understanding words