Reactive Content Selection in the Generation of Real-time Soccer Commentary
By Kumiko Tanaka-Ishii, Kôiti Hasida, I. Noda. 1998
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.
Subfields: Natural Language Processing, Natural Language Generation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Mirella Lapata
- Caiming Xiong
- Richard Socher
- Dragomir R. Radev
- Mohit Bansal
- Luke S. Zettlemoyer
- Graham Neubig
- Rui Zhang
In Natural Language Generation
- Ratish Puduppully
- Mirella Lapata
- Rui Zhang
- Li Dong
- Richard Socher
- Caiming Xiong
- Dragomir R. Radev
- Craig Thomson
Citations in the corpus
- Data-to-Text Generation with Content Selection and Planning (2018, background): “Like-wise, creating summaries of sports games has been a topic of interest since the early beginnings of generation systems (Robin 1994; Tanaka-Ishii et al. 1998).”
- Learning to Select, Track, and Generate for Data-to-Text (2019, methodology): “1 Data-to-Text Generation Data-to-text generation is a task for generating descriptions from structured or non-structured data including sports commentary (Tanaka-Ishii et al., 1998; Chen and Mooney, 2008; Taniguchi et al., 2019), weather forecast (Liang et al.”
- Generating Live Soccer-Match Commentary from Play Data (2019, background): “Tanaka-Ishii et al. (1998) and Chen et al. (2008) worked on this task, but with data of simulation soccer matches, in which both the input data and the commentaries are much simpler than ours.”
- ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “Applications include generating sports commentaries from game records (Tanaka-Ishii et al., 1998; Chen and Mooney, 2008; Taniguchi et al., 2019), weather forecasts (Liang et al.”