SignTrace system uses LLMs to identify Chinese Sign Language signs from descriptions

Researchers have developed SignTrace, a novel system designed to help users identify unfamiliar signs in Chinese Sign Language by using natural language descriptions. The system leverages LLM-based dictionary enrichment, action extraction, and a seven-channel retrieval process to match descriptions to over 6,699 sign entries. SignTrace has undergone user trials and demonstrated strong performance, achieving a 94.0% Hit@1 rate on a benchmark of 500 movement-description queries, significantly improving upon initial retrieval accuracy through a reranking mechanism. AI

IMPACT This system could improve accessibility and learning tools for sign language users and researchers.

RANK_REASON The item is an academic paper detailing a new system for sign language lookup. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Chinese Sign Language
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations
• SignTrace

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →