A multi-agent conversational system with heterogeneous data sources access

Type
Article

Authors
Eisman, Eduardo M.
Navarro, María
Castro, Juan Luis

KAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Online Publication Date
2016-01-28

Print Publication Date
2016-07

Date
2016-01-28

Abstract
In many of the problems that can be found nowadays, information is scattered across different heterogeneous data sources. Most of the natural language interfaces just focus on a very specific part of the problem (e.g. an interface to a relational database, or an interface to an ontology). However, from the point of view of users, it does not matter where the information is stored, they just want to get the knowledge in an integrated, transparent, efficient, effective, and pleasant way. To solve this problem, this article proposes a generic multi-agent conversational architecture that follows the divide and conquer philosophy and considers two different types of agents. Expert agents are specialized in accessing different knowledge sources, and decision agents coordinate them to provide a coherent final answer to the user. This architecture has been used to design and implement SmartSeller, a specific system which includes a Virtual Assistant to answer general questions and a Bookseller to query a book database. A deep analysis regarding other relevant systems has demonstrated that our proposal provides several improvements at some key features presented along the paper.

Citation
A multi-agent conversational system with heterogeneous data sources access 2016 Expert Systems with Applications

Publisher
Elsevier BV

Journal
Expert Systems with Applications

DOI
10.1016/j.eswa.2016.01.033

Additional Links
http://linkinghub.elsevier.com/retrieve/pii/S0957417416000567

Permanent link to this record