Going for GOAL: A Resource for Grounded Football Commentaries
This addresses the problem of grounding language in unpredictable, real-world scenarios for researchers in video-language AI, though it is incremental as it focuses on a new dataset and baseline tasks.
The authors introduced GOAL, a dataset of football highlight videos with live commentaries, to study dynamic language grounding due to the unpredictable nature of games. They provided state-of-the-art baselines for tasks like moment retrieval and commentary generation, showing models perform reasonably well.
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.