We propose a novel method for selecting coherent and diverse responses for a given dialogue context. The proposed method re-ranks response candidates generated from conversational models by using event causality relations between events in a dialogue history and response candidates (e.g., ``be stressed out'' precedes ``relieve stress''). We use distributed event representation based on the Role Factored Tensor Model for a robust matching of event causality relations due to limited event causality knowledge of the system. Experimental results showed that the proposed method improved coherency and dialogue continuity of system responses.
@article{arxiv.1906.09795,
title = {Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding},
author = {Shohei Tanaka and Koichiro Yoshino and Katsuhito Sudoh and Satoshi Nakamura},
journal= {arXiv preprint arXiv:1906.09795},
year = {2019}
}
Comments
Accepted by 1st Workshop NLP for Conversational AI, ACL 2019 Workshop (ConvAI)