A Hybrid Architecture for Multi-Party Conversational Systems

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 norms and machine learning and some insights after implementing and evaluating one on the finance domain.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-01520491
Contributor : Jean-Pierre Briot <>
Submitted on : Friday, May 12, 2017 - 2:41:15 PM
Last modification on : Thursday, March 21, 2019 - 2:32:17 PM
Long-term archiving on : Sunday, August 13, 2017 - 12:21:01 PM

File

1705.01214.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-01520491, version 1

Citation

Maira Gatti de Bayser, Paulo Cavalin, Renan Souza, Alan Braz, Heloisa Candello, et al.. A Hybrid Architecture for Multi-Party Conversational Systems. 2017. ⟨hal-01520491⟩

Share

Metrics

Record views

95

Files downloads

160