发表机构
Peking University; Loving Heart Society; Institute of Population Research, Peking University（北京大学; 爱心社; 北京大学人口研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SignTrace通过自然语言描述检索中文手语词典，结合LLM扩充与重排序，在500查询基准上实现94%的Hit@1，解决反向查找难题。
AI 中文摘要
当学习者记得一个手语的动作但不知道其含义或正式特征码时，识别不熟悉的手语是困难的。SignTrace通过自然语言访问中文手语词典，解决了这一长期存在的反向查找问题。该系统整合了基于大语言模型的词典扩充、动作提取、词典式改写、七通道检索以及针对6,699个条目的候选重排序。该系统已部署用于用户试验，并获得了积极非正式反馈。在基于词典构建的包含500个动作描述查询的基准上评估，实现了94.0%的Hit@1、97.4%的Hit@9以及0.9540的平均倒数排名。重排序将Hit@1从71.8%提升至94.0%，而组件分析显示了扩充条目描述的贡献。六并发查询时，中位查询处理时间为13.37秒。通过将日常动作描述与记录的手语及其含义相连接，SignTrace为识别不熟悉手语提供了实用工具。基准中词典来源的措辞和先验选择限制了对用户独立生成描述的泛化能力。
英文摘要
Identifying an unfamiliar sign is difficult when a learner remembers its movement but does not know its meaning or formal feature codes. SignTrace addresses this longstanding reverse-lookup problem through natural-language access to a Chinese sign-language dictionary. The system integrates LLM-based dictionary enrichment, action extraction, dictionary-style rewriting, seven-channel retrieval, and candidate reranking over 6,699 entries. It has been deployed for user trials and has received positive informal feedback. Evaluation on a dictionary-derived benchmark of 500 movement-description queries yields 94.0% Hit@1, 97.4% Hit@9, and a mean reciprocal rank of 0.9540. Reranking increases Hit@1 from 71.8% to 94.0%, while component analyses show the contribution of enriched entry descriptions. Median query-processing time is 13.37 seconds with six concurrent queries. By connecting everyday movement descriptions to documented signs and meanings, SignTrace provides a practical tool for identifying unfamiliar signs. Dictionary-derived wording and prior selection within the benchmark limit generalization to descriptions independently produced by users.
CommentsIncludes reproducibility data and method documentation
