arXiv Analytics

Sign in

arXiv:1709.03968 [cs.CL]AbstractReferencesReviewsResources

Affective Neural Response Generation

Nabiha Asghar, Pascal Poupart, Jesse Hoey, Xin Jiang, Lili Mou

Published 2017-09-12Version 1

Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content. We take a step in this direction by proposing three novel ways to incorporate affective/emotional aspects into long short term memory (LSTM) encoder-decoder neural conversation models: (1) affective word embeddings, which are cognitively engineered, (2) affect-based objective functions that augment the standard cross-entropy loss, and (3) affectively diverse beam search for decoding. Experiments show that these techniques improve the open-domain conversational prowess of encoder-decoder networks by enabling them to produce emotionally rich responses that are more interesting and natural.