Most sign-recognition tools learn by watching thousands of example videos. But labeled ASL video is scarce. A team tried something different: give the computer a map of how signs are actually built, the way a linguist understands them. It worked.

Sign language tech needs real signing videos, and gathering them is slow work. What if collecting data could be a game? Researchers built a signing version of Battleship to find out.

Signs are made of building blocks, the way spoken words are made of sounds. This study asked how best to teach a computer to spot those blocks. The answer was surprisingly human: start with the easy ones, then build up.

How common is a sign? How is it built? Does it look like what it means? ASL-LEX answers those questions for thousands of ASL signs, in one free, searchable place. It started with about 1,000 signs and grew to 2,723, and it has quietly become a foundation for sign language research and technology.

On April 16-17, 2026, the Deaf Center hosted the first SLxAI Summit at Boston University. 220 people from 50+ organizations and 14 countries came together around sign language and AI, with Deaf leadership at the center and ethics leading the way.

Sign language AI learns from video of real people signing. That data is personal, and the choices around it carry weight. A team of deaf and hearing experts maps the questions everyone building these tools should ask.

Imagine being able to look up an unfamiliar ASL sign by simply demonstrating it to your device. Whether you're a fluent signer or just beginning to learn, this type of interaction could transform accessibility in technology—think of ASL-compatible assistants like Siri or Alexa or search engines that understand signed queries. This vision is one step closer to reality thanks to the ASL Citizen dataset, a collaborative project we worked on with Microsoft Research, University of

A dataset to train computers to recognize isolated signs.

Sign language AI runs on video of real deaf people signing. That raises hard questions about privacy, ownership, and who gets a say. Our team laid out a framework for building this technology responsibly.