NLP & Speech

Columbia researchers are using natural language processing tools to extract text from news reports, feeds, and social media to automatically summarize key points.

Overcoming language barriers so disaster relief teams can move quickly to aid areas in most need

Using AI techniques, Kathleen McKeown and Julia Hirschberg are creating an automated, universal sentiment detection system for new languages, including low-resource languages where translators are few.

We’re not ready for AI, says the winner of a new $1 Million AI prize

Regina Barzilay (PhD '03), the first winner of the Squirrel AI Award, talks to MIT Tech Review on why the pandemic should be a wake-up call.

About

The Speech and Natural Language Processing groups do fundamental work in language understanding and generation with applications to a wide variety of topics, including summarization, argumentation, persuasion, sentiment, detecting deceptive, emotional and charismatic speech, text-to-speech synthesis, analysis of social media to detect mental illness, abusive language, and radicalization.

The groups collaborate closely on many research projects with each other, with language faculty in other universities, and with Columbia faculty in other disciplines. They also mentor a very large number of master’s and undergraduate research project students who participate in their research each semester. They have regular talks for faculty, students, and the larger New York area community.