Multi-agent explanation strategies in real-time domains

Authors:
Kumiko Tanaka-Ishii;Ian Frank
Affiliations:
University of Tokyo, Hongo Bunkyo-ku, Tokyo, Japan;Electrotechnical Laboratory, Tsukuba, Ibaraki, Japan
Venue:
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Year:
2000

Citing 1
Cited 4

Reactive content selection in the generation of real-time soccer commentary

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2

Walkie-Talkie MIKE

RoboCup 2001: Robot Soccer World Cup V
And the Fans Are Going Wild! SIG plus MIKE

RoboCup 2000: Robot Soccer World Cup IV
An Instance vs. The Instance

Minds and Machines
Conceptual representation for a soccer commentary generator

RoboCup 2005

Quantified Score

Hi-index	0.00

Visualization

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.