Categories: FAANG

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…
AI Generated Robotic Content

Recent Posts

Testing MiniMax-H3 Physics knowledge Pt2

Some weeks ago, I posted a set of experiments to "understand" the physical knowledge of…

8 seconds ago

Monitoring production agent lifecycle with AWS DevOps Agent and AgentCore Evaluations

Multi-agent systems in production experience issues in ways that traditional monitoring misses. For example, the…

5 mins ago

The 9 Best TV Shows to Stream This Month (September 2026)

South Park, Slow Horses, Neon Genesis Evangelion, and a Lego-fied Mandalorian are just a few…

1 hour ago

Tiny nanolaser could cut computer energy use in half

Scientists have created an ultra-small nanolaser that could eventually allow microchips to transmit information with…

1 hour ago

Kirby but it’s the Truman Show / MiniMAX H3 Test #7

Hi everyone! When I saw the new trailer for Kirby & The World Beyond I…

1 day ago

Reminder: Live Today — Building AI Agents, The Loop

Quick note — The Loop’s first session is today, 4:30 PM PDT, live on Zoom.Free, monthly, and genuinely…

1 day ago