苹果发布 DiscoSign 系统实现文本到手语转写
DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
苹果搞了个叫 DiscoSign 的东西，能更智能地把文字翻译成手语，解决了传统方法忽略上下文的问题。
苹果的 DiscoSign 系统解决了传统手语处理系统忽略上下文关联的问题，通过其基于大型语言模型的框架，能够处理实体空间指代、问答从句等手语特有的复杂结构。
DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic research. We address three key phenomena within our modular Large Language Model (LLM)-based translation framework: (i) spatial coreference resolution, where entities maintain consistent spatial locations throughout discourse; (ii) Question-Answer Clauses (QACs), pseudocleft structures serving…
