手语生成的强度建模：一种计算方法
Modeling Intensification for Sign Language Generation: A Computational Approach
AI总结：
本文针对手语生成模型缺乏韵律表现的问题，提出基于语言学策略的强度建模方法，通过标注PHOENIX-14T数据集并训练Transformer模型，显著提升了生成手语的质量和人类评价偏好。
摘要：
端到端手语生成模型无法准确表示手语中的韵律。时间和空间变化的缺乏导致生成的演示质量较差，使人类口译员感到困惑。本文旨在通过以数据驱动的方式对强度进行建模来改善生成手语中的韵律。我们提出了基于手语语言学的不同策略，这些策略说明了强度修饰语如何在注释中表示。为了采用我们的策略，我们首先对基准数据集PHOENIX-14T（一个德国手语数据集）的一个子集进行不同强度级别的标注。然后，我们使用一个有监督的强度标注器来扩展已标注的数据集，并为其剩余部分获得标签。这个增强后的数据集随后被用于训练最先进的Transformer模型以进行手语生成。我们发现，在使用自动指标进行评估时，我们在强度建模方面的努力产生了更好的结果。人类评估也表明，使用我们的模型生成的视频获得了更高的偏好。
英文摘要：
End-to-end sign language generation models do not accurately represent the prosody in sign language. A lack of temporal and spatial variations leads to poor-quality generated presentations that confuse human interpreters. In this paper, we aim to improve the prosody in generated sign languages by modeling intensification in a data-driven manner. We present different strategies grounded in linguistics of sign language that inform how intensity modifiers can be represented in gloss annotations. To employ our strategies, we first annotate a subset of the benchmark PHOENIX-14T, a German Sign Language dataset, with different levels of intensification. We then use a supervised intensity tagger to extend the annotated dataset and obtain labels for the remaining portion of it. This enhanced dataset is then used to train state-of-the-art transformer models for sign language generation. We find that our efforts in intensification modeling yield better results when evaluated with automatic metrics. Human evaluation also indicates a higher preference of the videos generated using our model.
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。
