NLP & Speech

2002 paper by Michael Collins earns Test-of-Time award at NAACL

“Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms” laid the foundation for how to use machine learning methods across a range of NLP tasks.

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.

Research That Studied Data From Social Media, Automatic Summarization, and Spatial Relations Accepted to NAACL 2019

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.