A multi-agent conversational system with heterogeneous data sources access

作者：

Highlights：

• We present a multi-agent conversational architecture for heterogeneous data sources.

• Expert agents are specialized in accessing different knowledge sources.

• Decision agents coordinate expert agents to provide a coherent final answer to users.

• This generic architecture is used to make a SmartSeller for a bookstore.

• A comparative analysis demonstrates several improvements regarding existing systems.

摘要

•We present a multi-agent conversational architecture for heterogeneous data sources.•Expert agents are specialized in accessing different knowledge sources.•Decision agents coordinate expert agents to provide a coherent final answer to users.•This generic architecture is used to make a SmartSeller for a bookstore.•A comparative analysis demonstrates several improvements regarding existing systems.

论文关键词：Natural language interfaces,Virtual assistants,Embodied conversational agents,Multi-agent systems,Semantic grammars,Ontologies

论文评审过程：Received 2 June 2015, Revised 20 January 2016, Accepted 21 January 2016, Available online 28 January 2016, Version of Record 15 February 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.01.033