Cornell NLP

The Cornell Natural Language Processing Group is a diverse team of researchers interested in computational models of human language and machine learning. We apply a computational lens to a broad set of projects in the areas of linguistic analysis, natural language understanding systems, social science, and humanities. We are a cross-campus group located both in Ithaca and the new Tech campus in NYC. The group includes members from the departments of Computer Science, Information Science, and Linguistics.

A small sampling of problems we are interested in are (in alphabetical order): argumentation mining, grounded language learning, information and opinion extraction, lexicon and grammar induction, paraphrase acquisition, situated language understanding, syntactic parsing, question-answering, semantic parsing, sentiment analysis, similarity-based methods, and text summarization.

Related Sites

Recent News

Tianze Shi awarded an inaugural Bloomberg Data Science Fellowship for 2018-2019 [July 2018]

Laure Thompson and David Mimno win Best NLP Engineering Experiment Paper Award for their paper "Authorless Topic Models: Biasing Models Away from Known Structure" at COLING 2018 [June 2018]

David Mimno recognized as an outstanding writing mentor for the COLING 2018 conference [April 2018]

Alane Suhr, Srinivasan Iyer (UW), and Yoav Artzi win Outstanding Paper Award at NAACL 2018 for the paper "Learning to Map Context-Dependent Sentences to Executable Formal Queries" [April 2018]

Alane Suhr awarded an NSF Graduate Research Fellowship [April 2018]

"Thumbs up? Sentiment Classification using Machine Learning Techniques" (2002) by Bo Pang (Cornell CS PhD 2006), Lillian Lee and Shivakumar Vaithyanathan (IBM) receives the inaugural Computational Linguistics Test-of-Time Award [March 2018]

Cristian Danescu-Niculescu-Mizil and Yoav Artzi each receive a 2017 Google Faculty Research Award [March 2018]

Cristian Danescu-Niculescu-Mizil receives NSF CAREER award for research on artificial conversational intuition [March 2018]

The AI2 NLP Highlights podcast interviews Vlad Niculae about sparse and structured attention mechanisms [March 2018]