arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.12876cs.CVcs.CL
收藏

无Gloss端到端手语翻译

Gloss-Free End-to-End Sign Language Translation

Zhejiang University(浙江大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Kezhou Lin, Xiaohan Wang, Linchao Zhu, Ke Sun, Bang Zhang, Yi Yang

AI总结:

本文提出无Gloss端到端手语翻译框架GloFE,通过从文本提取概念作为弱中间表示并进行对比学习,在OpenASL和How2Sign上取得最先进结果。

摘要:

在本文中,我们解决无Gloss标注的手语翻译(SLT)问题。尽管像Gloss这样的中间表示已被证明有效,但Gloss标注难以获取,尤其是大规模获取。这限制了翻译数据集的领域覆盖范围,从而阻碍了现实世界的应用。为了缓解这一问题,我们设计了无Gloss端到端手语翻译框架(GloFE)。我们的方法通过利用手语与相应口语翻译之间共享的底层语义,提升了无Gloss设置下SLT的性能。从文本中提取常见概念,并将其用作弱形式的中间表示。这些概念的全局嵌入被用作交叉注意力的查询,以在学习到的视觉特征中找到相应信息。我们以对比的方式,鼓励包含这些概念的样本之间查询结果的相似性,并降低不包含这些概念的样本之间的相似性。我们在包括OpenASL和How2Sign在内的大规模数据集上取得了最先进的结果。代码和模型将在 https://github.com/HenryLittle/GloFE 上提供。

英文摘要:

In this paper, we tackle the problem of sign language translation (SLT) without gloss annotations. Although intermediate representation like gloss has been proven effective, gloss annotations are hard to acquire, especially in large quantities. This limits the domain coverage of translation datasets, thus handicapping real-world applications. To mitigate this problem, we design the Gloss-Free End-to-end sign language translation framework (GloFE). Our method improves the performance of SLT in the gloss-free setting by exploiting the shared underlying semantics of signs and the corresponding spoken translation. Common concepts are extracted from the text and used as a weak form of intermediate representation. The global embedding of these concepts is used as a query for cross-attention to find the corresponding information within the learned visual features. In a contrastive manner, we encourage the similarity of query results between samples containing such concepts and decrease those that do not. We obtained state-of-the-art results on large-scale datasets, including OpenASL and How2Sign. The code and model will be available at https://github.com/HenryLittle/GloFE.

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。

↑