Paper Info
Title
Multi-agent explanation strategies in real-time domains
Abstract
We examine the benefits of using multiple agents to produce explanations. In particular, we identify the ability to construct prior plans as a key issue constraining the effectiveness of a single-agent approach. We describe an implemented system that uses multiple agents to tackle a problem for which prior planning is particularly impractical: real-time soccer commentary. Our commentary system demonstrates a number of the advantages of decomposing an explanation task among several agents. Most notably, it shows how individual agents can benefit from following different discourse strategies. Further, it illustrates that discourse issues such as controlling interruption, abbreviation, and maintaining consistency can also be decomposed: rather than considering them at the single level of one linear explanation they can also be tackled separately within each individual agent. We evaluate our system's output, and show that it closely compares to the speaking patterns of a human commentary team.
Year
DOI
Venue
2000
10.3115/1075218.1075239
ACL
Keywords
Field
DocType
different discourse strategy,prior plan,real-time soccer commentary,discourse issue,real-time domain,multi-agent explanation strategy,linear explanation,explanation task,commentary system,human commentary team,multiple agent,individual agent,real time
Computer science,Artificial intelligence,Machine learning
Conference
Volume
Citations 
PageRank 
P00-1
4
0.90
References 
Authors
3
2
Name
Order
Citations
PageRank
Kumiko Tanaka-Ishii126136.69
Ian Frank220125.27