SCI Assistant Professor Malihe Alikhani recently co-authored a paper encouraging the natural language processing (NLP) community to include signed languages in their research. NLP is an area of study in computer science that focuses on helping computers understand human language and allowing people to communicate using technological tools like machine translation, voice-controlled assistants, and chatbots. However, NLP research usually focuses only on spoken language; Alikhani's paper, titled "Including Signed Languages in Natural Language Processing," urges NLP researchers to acknowledge sign language processing (SLP) as a research area with high social and scientific impact.
SLP studies often rely on computer vision, but this approach usually does not take into account the complexity of signed languages. NLP tools are better able to process more linguistic properties, such as hand gestures, facial expressions, and head and body movements that can be used to convey multiple words at once. Alikhani's paper reviews the limitations of current SLP models, identifies the open challenges to extend NLP to signed languages, and offers recommendations for including signed language in NLP research. Alikhani's co-authors include Amit Moryossef of Bar-Ilan University in Israel, Julie Hochgesang of Gallaudet University in Washington, D.C., Yoav Goldberg of Bar-Ilan University and the Allen Institute for AI, and Kayo Yin of the Language Technologies Institute at Carnegie Mellon University. The paper won the Best Theme Paper award at this month's 59th Annual Meeting of the Association for Computational Linguistics.
Alikhani teaches in the Department of Computer Science at SCI. Her primary research interests are in the fields of natural language processing and cognitive science with broader interests in computational social sciences.