The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty
ACM Computing Surveys (CSUR)
Generating Natural Language under Pragmatic Constraints
Generating Natural Language under Pragmatic Constraints
MIKE: An Automatic Commentary System for Soccer
ICMAS '98 Proceedings of the 3rd International Conference on Multi Agent Systems
Planning natural language referring expressions
ACL '82 Proceedings of the 20th annual meeting on Association for Computational Linguistics
Automatic Soccer Commentary and RoboCup
RoboCup-98: Robot Soccer World Cup II
From data to speech: a general approach
Natural Language Engineering
Proceedings of the 17th annual ACM symposium on User interface software and technology
Multi-agent explanation strategies in real-time domains
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Collective content selection for concept-to-text generation
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
An Introduction to a New Commentator for RoboCup 3D Soccer Simulation
SIMPAR '08 Proceedings of the 1st International Conference on Simulation, Modeling, and Programming for Autonomous Robots
Perspective-oriented generation of football match summaries: Old tasks, new challenges
ACM Transactions on Speech and Language Processing (TSLP)
Automated Event Recognition for Football Commentary Generation
International Journal of Gaming and Computer-Mediated Simulations
Hi-index | 0.00 |
MIKE is an automatic commentary system that generates a commentary of a simulated soccer game in English, French, or Japanese.One of the major technical challenges involved in live sports commentary is the reactive selection of content to describe complex, rapidly unfolding situation. To address this challenge, MIKE employs importance scores that intuitively capture the amount of information communicated to the audience. We describe how a principle of maximizing the total gain of importance scores during a game can be used to incorporate content selection into the surface generation module, thus accounting for issues such as interruption and abbreviation.Sample commentaries produced by MIKE are presented and used to evaluate different methods for content selection and generation in terms of efficiency of communication.