Get Started
Home
Topics
Search
Library
Research questionHow can text-to-ASL gloss translation preserve discourse coherence across sentences?Sentence-level translation can lose entity locations and stable sign choices as discourse unfolds. Standard translation metrics may not reveal these coherence failures.
AI
Evaluation & Benchmarks
Natural Language Processing
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.DiscoSign: Discourse-Aware Text to Sign Language Gloss TranslationThe source describes DiscoSign, a modular LLM-based framework evaluated on sentence-level and discourse-level datasets for English-to-ASL gloss translation. It reports improved spatial consistency and entity tracking while maintaining competitive single-sentence quality, alongside metrics for the targeted discourse phenomena.research paper · Sep 2, 2026
Related questions
How can sign language translation models capture asynchronous lip cues and recognize fingerspelled terms without detailed supervision?How can vision-language models express visually grounded answers with context-appropriate information structure?How can systems fact-check multilingual spoken dialogue when claims span turns and ASR distorts the text?How can multilingual question answering remain consistent across languages without erasing culturally appropriate differences?