YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus

NeurIPS(2023)

引用 0|浏览3
暂无评分
摘要
Machine learning for sign languages is bottlenecked by data. In this paper, we present YouTube-ASL, a large-scale, open-domain corpus of American Sign Language (ASL) videos and accompanying English captions drawn from YouTube. With ~1000 hours of videos and >2500 unique signers, YouTube-ASL is ~3x as large and has ~10x as many unique signers as the largest prior ASL dataset. We train baseline models for ASL to English translation on YouTube-ASL and evaluate them on How2Sign, where we achieve a new finetuned state of the art of 12.39 BLEU and, for the first time, report zero-shot results.
更多
查看译文
关键词
parallel corpus,sign,youtube-asl,large-scale,open-domain,language-english
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要