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. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Computation and Language | Architecture,Natural language interaction,Computer science,Utterance,Natural language processing,Artificial intelligence |
DocType | Volume | Citations |
Journal | abs/1705.01214 | 0 |
PageRank | References | Authors |
0.34 | 9 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Maira Gatti de Bayser | 1 | 0 | 2.37 |
Paulo Rodrigo Cavalin | 2 | 83 | 16.37 |
Renan Souza | 3 | 0 | 0.68 |
Alan Braz | 4 | 0 | 1.35 |
Heloisa Candello | 5 | 7 | 3.21 |
Claudio S. Pinhanez | 6 | 650 | 87.79 |
Jean-Pierre Briot | 7 | 623 | 85.90 |