NLP Seminar: Natural Language Processing for Signed Languages
Kayo Yin, from UC Berkeley, is presenting her most recent works on Natural Language Processing for Signed Languages.
You can join in CE16 or online.
Abstract:
Signed languages are the primary means of communication for many deaf and hard-of-hearing (DHH) individuals. Since signed languages exhibit all the fundamental linguistic properties of natural language, we believe that tools and theories of Natural Language Processing (NLP) are crucial for its modeling. However, existing research in sign language processing seldom attempts to explore and leverage the linguistic organization of signed languages.
In this lecture, she will talk about why NLP researchers should include signed languages in their research, best practices for conducting sign language research, and some of the challenges in sign language processing today. She will also present two recent projects that take steps in extending NLP to signed languages: 1) modeling handshapes to analyze different pressures for communication efficiency in American Sign Language (ASL) and 2) using AI to make STEM education more accessible to DHH students.
You can join in CE16 or online.
Abstract:
Signed languages are the primary means of communication for many deaf and hard-of-hearing (DHH) individuals. Since signed languages exhibit all the fundamental linguistic properties of natural language, we believe that tools and theories of Natural Language Processing (NLP) are crucial for its modeling. However, existing research in sign language processing seldom attempts to explore and leverage the linguistic organization of signed languages.
In this lecture, she will talk about why NLP researchers should include signed languages in their research, best practices for conducting sign language research, and some of the challenges in sign language processing today. She will also present two recent projects that take steps in extending NLP to signed languages: 1) modeling handshapes to analyze different pressures for communication efficiency in American Sign Language (ASL) and 2) using AI to make STEM education more accessible to DHH students.
Bio:
Kayo Yin is a second year PhD student at UC Berkeley advised by Jacob Steinhardt and Dan Klein. She currently works on LLM interpretability and sign language processing. Before that, she was a Master’s student at Carnegie Mellon University advised by Graham Neubig, and she completed her undergraduate studies at École Polytechnique in 2020. Her research has been recognized by an ACL Best Resource Paper award, an EMNLP Best Paper Honorable Mention award, an ACL Best Theme Paper award, and the Thomas Clarkson medal. She is the recipient of a Siebel Scholarship and a Future of Life PhD fellowship.
Kayo Yin is a second year PhD student at UC Berkeley advised by Jacob Steinhardt and Dan Klein. She currently works on LLM interpretability and sign language processing. Before that, she was a Master’s student at Carnegie Mellon University advised by Graham Neubig, and she completed her undergraduate studies at École Polytechnique in 2020. Her research has been recognized by an ACL Best Resource Paper award, an EMNLP Best Paper Honorable Mention award, an ACL Best Theme Paper award, and the Thomas Clarkson medal. She is the recipient of a Siebel Scholarship and a Future of Life PhD fellowship.
Practical information
- Informed public
- Free
Organizer
- Antoine Bosselut (NLP lab)