Going for GOAL: A Resource for Grounded Football Commentaries
Recent video+language datasets cover domains where the interaction is highly structured, such as instructional videos, or where the interaction is scripted, such as TV shows. Both of these properties can lead to spurious cues to be exploited by models rather than learning to ground language. In this paper, we present GrOunded footbAlL commentaries (GOAL), a novel dataset of football (or `soccer') highlights videos with transcribed live commentaries in English. As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding. We also provide state-of-the-art baselines for the following tasks: frame reordering, moment retrieval, live commentary retrieval and play-by-play live commentary generation. Results show that SOTA models perform reasonably well in most tasks. We discuss the implications of these results and suggest new tasks for which GOAL can be used. Our codebase is available at: https://gitlab.com/grounded-sport-convai/goal-baselines.
Code (1)
Tasks
Moment RetrievalRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GOAL: Towards Benchmarking Few-Shot Sports Game Summarization
Sports game summarization aims to generate sports news based on real-time commentaries. The task has attracted wide research attention but is still under-explored probably due to the lack of corresponding English dataset…
BenchmarkingRating evaluation of sports development efficiency using statistical analysis: evidence from Russian football
Increasing investments into various dimensions of sports draw a significant amount of attention to the way these resources are being managed and which organizations achieve development goals with higher efficiency. This …
Explainable expected goal models for performance analysis in football analytics
The expected goal provides a more representative measure of the team and player performance which also suit the low-scoring nature of football instead of score in modern football. The score of a match involves randomness…
Explainable artificial intelligenceA Machine Learning Approach for Player and Position Adjusted Expected Goals in Football (Soccer)
Football is a very result-driven industry, with goals being rarer than in most sports, so having further parameters to judge the performance of teams and individuals is key. Expected Goals (xG) allow further insight than…
Binary ClassificationPositionTransformer-Based Neural Marked Spatio Temporal Point Process Model for Football Match Events Analysis
With recently available football match event data that record the details of football matches, analysts and researchers have a great opportunity to develop new performance metrics, gain insight, and evaluate key performa…
Point Processes