arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2408.13585cs.CLcs.CV

FLEURS-ASL:将美国手语纳入大规模多语言多任务评估

FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluation

Google(谷歌)

Garrett Tanzer

AI总结:

本文提出 FLEURS-ASL 基准,将美国手语扩展至多语言多任务评估中,支持 ASL 与 200 种文本或 102 种语音语言间的翻译,并提供统一建模基线,揭示了前沿多模态模型对 ASL 的理解不足。

摘要:

手语翻译历来处于主流机器翻译研究的边缘。为了帮助促进各领域的融合,我们引入了 FLEURS-ASL,它是多路并行基准 FLORES(针对文本)和 FLEURS(针对语音)的扩展,以支持其首个手语(作为视频)——美国手语,由 5 名认证聋人译员翻译。FLEURS-ASL 可用于评估多种任务——主要是句子和语篇级别的翻译——在 ASL 与 200 种其他语言的文本之间,或 102 种语言的语音之间进行。我们使用一种统一建模方法提供了从 ASL 到英文文本任务的基线,该方法在 34 秒的上下文窗口中结合了时间戳标记和先前的文本标记,并在 YouTube-ASL 的随机视频片段上进行了训练。该模型达到或超越了短语级基线的性能,同时支持大量新任务。我们还使用 FLEURS-ASL 表明,多模态前沿模型对 ASL 几乎没有理解能力,这凸显了在标准评估套件中纳入手语的重要性。

英文摘要:

Sign language translation has historically been peripheral to mainstream machine translation research. In order to help converge the fields, we introduce FLEURS-ASL, an extension of the multiway parallel benchmarks FLORES (for text) and FLEURS (for speech) to support their first sign language (as video), American Sign Language, translated by 5 Certified Deaf Interpreters. FLEURS-ASL can be used to evaluate a variety of tasks -- primarily sentence- and discourse-level translation -- between ASL and 200 other languages as text, or 102 languages as speech. We provide baselines for tasks from ASL to English text using a unified modeling approach that incorporates timestamp tokens and previous text tokens in a 34-second context window, trained on random video clips from YouTube-ASL. This model meets or exceeds the performance of phrase-level baselines while supporting a multitude of new tasks. We also use FLEURS-ASL to show that multimodal frontier models have virtually no understanding of ASL, underscoring the importance of including sign languages in standard evaluation suites.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑