比賽時間匹配：朝向自動足球比賽評論生成

MatchTime: Towards Automatic Soccer Game Commentary Generation

June 26, 2024

作者: Jiayuan Rao, Haoning Wu, Chang Liu, Yanfeng Wang, Weidi Xie

cs.AI

摘要

足球是一項全球受歡迎的運動，擁有廣泛的觀眾群。本文考慮構建一個自動足球比賽評論模型，以提升觀眾的觀賞體驗。總的來說，我們做出以下貢獻：首先，觀察現有數據集中普遍存在的視頻文本不一致性問題，我們手動為49場比賽標註了時間戳，建立了一個更穩健的足球比賽評論生成基準，稱為SN-Caption-test-align；其次，我們提出了一個多模態時間對齊流程，以自動在大規模上校正和過濾現有數據集，創建了一個更高質量的足球比賽評論數據集進行訓練，命名為MatchTime；第三，基於我們的精心策劃數據集，我們訓練了一個自動評論生成模型，名為MatchVoice。大量實驗和消融研究已經證明了我們對齊流程的有效性，以及在精心策劃的數據集上訓練模型實現了評論生成的最新性能，展示了更好的對齊可以在下游任務中帶來顯著的性能改進。

English

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 datasets achieves state-of-the-art performance for commentary generation, showcasing that better alignment can lead to significant performance improvements in downstream tasks.