MatchTime: Towards Automatic Soccer Game Commentary Generation
This work addresses the challenge of improving viewing experience for soccer audiences by enhancing dataset alignment, though it is incremental as it builds on existing commentary generation methods.
The paper tackled the problem of video-text misalignment in soccer game commentary datasets by manually annotating timestamps for 49 matches and proposing a multi-modal temporal alignment pipeline to create a higher-quality dataset, resulting in a model that achieves state-of-the-art performance for commentary generation.
Soccer is a globally popular sport with a vast audience, in this paper, we consider constructing an automatic soccer game commentary model to improve the audiences' viewing experience. In general, we make the following contributions: First, observing the prevalent video-text misalignment in existing datasets, we manually annotate timestamps for 49 matches, establishing a more robust benchmark for soccer game commentary generation, termed as SN-Caption-test-align; Second, we propose a multi-modal temporal alignment pipeline to automatically correct and filter the existing dataset at scale, creating a higher-quality soccer game commentary dataset for training, denoted as MatchTime; Third, based on our curated dataset, we train an automatic commentary generation model, named MatchVoice. Extensive experiments and ablation studies have demonstrated the effectiveness of our alignment pipeline, and training model on the curated dataset achieves state-of-the-art performance for commentary generation, showcasing that better alignment can lead to significant performance improvements in downstream tasks.