A Hybrid Architecture for Multi-Party Conversational Systems
Computation and Language
2017-05-08 v2
Abstract
Multi-party Conversational Systems are systems with natural language interaction between one or more people or systems. From the moment that an utterance is sent to a group, to the moment that it is replied in the group by a member, several activities must be done by the system: utterance understanding, information search, reasoning, among others. In this paper we present the challenges of designing and building multi-party conversational systems, the state of the art, our proposed hybrid architecture using both rules and machine learning and some insights after implementing and evaluating one on the finance domain.
Cite
@article{arxiv.1705.01214,
title = {A Hybrid Architecture for Multi-Party Conversational Systems},
author = {Maira Gatti de Bayser and Paulo Cavalin and Renan Souza and Alan Braz and Heloisa Candello and Claudio Pinhanez and Jean-Pierre Briot},
journal= {arXiv preprint arXiv:1705.01214},
year = {2017}
}