English(EN) DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation

新的DualAnchor框架提高了手语翻译的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-31 04:00

研究人员开发了DualAnchor，这是一个新的手语翻译（SLT）框架，旨在提高翻译文本的流畅性和词汇细节的准确性。该框架解决了两个关键问题：语言先验退化，即现有方法未能充分利用大型语言模型（LLM）的全部能力；以及词汇保真度差距，即句子级对齐未能实现细粒度的词语准确性。DualAnchor采用Token级先验锚定（TPA）来保持LLM的语言先验，并采用最优传输对齐（OTA）来增强视觉-文本匹配，在PHOENIX-2014T和CSL-Daily等基准数据集上取得了强劲的性能。 AI

影响通过提高流畅性和词汇准确性，改进了基于LLM的手语翻译。

排序理由该集群包含一篇详细介绍手语翻译新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍手语翻译新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 77 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Hongbin Zhang, Junhao Liu, Xuefeng Bai, Youcheng Pan, Yang Xiang, Kehai Chen · 2026-07-31 04:00

DualAnchor：在无标注手语翻译中保留语言先验并提高词汇保真度

arXiv:2607.27614v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-language text, to increasingly adopt LLMs as textual backbones. However, despite their…

本文如何被排名

报道来源 [1]

DualAnchor：在无标注手语翻译中保留语言先验并提高词汇保真度

相关实体

相关话题