Publication
INLG 2017
Conference paper

Neural response generation for customer service based on personality traits

Abstract

We present a neural response generation model that generates responses conditioned on a target personality. The model learns high level features based on the target personality, and uses them to update its hidden state. Our model achieves performance improvements in both perplexity and BLEU scores over a baseline sequence-to-sequence model, and is validated by human judges.

Date

04 Sep 2017

Publication

INLG 2017

Authors

Share