提出Gated-Logarithmic Transformer，提升手语翻译的时序建模能力
GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation
- 引入门控对数机制，更好捕捉手语的时间序列特性
- 在多指标上超越Transformer及融合模型，显著提升翻译准确率
- 适合关注手语识别与无障碍交流的研究者与开发者
机器翻译在消除语言障碍中起关键作用，但其在手语机器翻译（SLMT）中的应用仍较少被探索。现有手语翻译方法多采用Transformer网络，因手语动态性强而表现不佳。本文提出一种新型门控对数变换器（GLoT），将手语作为时间序列数据建模，以捕捉其长期时序依赖关系。我们在Sign-to-Gloss-to-Text翻译任务中，对GLoT与Transformer及Transformer-fusion模型进行了全面评估。结果表明，GLoT在各项指标上均持续优于基线模型，展现出解决聋人及听力障碍群体沟通难题的巨大潜力。
原文摘要 · Abstract (English)
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。