Eugene Charniak University Professor of Computer Science

Professor Charniak became interested in computers late in his education as a physics undergraduate at the University of Chicago. He spent the summer between his junior and senior years programming a computer at Argonne National Laboratory for a high-energy physics experiment. During his senior year he started to read more about computer science. Having originally applied to graduate school in physics, he switched his focus and went to M.I.T. to study computer science, where he received his doctorate.

Brown Affiliations

Research Areas

scholarly work

View My Full Publications List Here.

research overview

Eugene Charniak is interested in programming computers to understand language so that they will be able to perform such tasks as answering questions and holding a conversation. Prof. Charniak and his students write programs that collect statistical information about language from large amounts of text then apply the statistics to new examples.


Other recent work uses statistics that relate the probability of a particular referent based upon a variety of factors: how far back it is in the text, the typical gender of the antecedent phrase, etc. His motivation is primarily theoretical, but there are also many applications for this research, including automatic language translation, computer telephone operators, and web search engines that answer questions.




research statement

Eugene Charniak is interested in programming computers to understand language so that they will be able to perform such tasks as answering questions and holding a conversation. This is far beyond our current capabilities, so research proceeds by dividing the problem up into manageable subparts. Prof. Charniak's research is called "statistical language learning." He and his students write programs that collect statistical information about language from large amounts of text, then apply the statistics to new examples. For example, much of his recent research has been on statistical models of syntactic parsing—grammatically identifying parts of speech and learning the rules for sentence formation, an exercise akin to the sentence diagramming that most of us did in school. Most researchers believe it is a small but important step toward true language understanding.


Prof. Charniak and his students have also been looking at statistics-based programs for determining the referents of pronouns. For example, in the sentence, "After Helen cleaned the piano she played some Brahms," the program would be trained to figure out that "she" refers to "Helen" (and not "the piano"). He uses statistics that relate the probability of a particular referent based upon factors like how far back it is in the text, the typical gender of the antecedent phrase ("Helen" vs. "the piano"), etc. His motivation is primarily theoretical, an effort to learn how language understanding is possible. However, there are also many applications for this research, including automatic language translation, computer telephone operators, and web search engines that answer questions.

funded research

Global Autonomous Language Exploration (PI), International Business Machines Corporation, $275,000, 11/7/2005-10/31/2006

Learning Syntactic Semantic Knowledge for Parsing (PI), National Science Foundation-Information Technology Research, $500,000, 2001-2004

Robust Knowledge Discovery from Parallel Speech and Text (PI), National Science Foundation, $300,000, 2000-2004

Structured Statistical Learning (PI), National Science Foundation, $775,420, 1997-2000

AI Approaches to Statistical Language Models (PI), Office of Naval Research, $304,384, 1996-1999

Improved Statistical Language Models (PI), National Science Foundation, $224,914, 1994-1997

High-Performance Computing Environments (PI), Defense Advanced Research Projects Agency (DARPA), $2,697,175, 1991-1994

High-Performance Design Environments (PI), Defense Advanced Research Projects Agency (DARPA)/Office of Naval Research, $2,580,000, 1991-1996

A Probabilistic Approach to Text Understanding (PI), Office of Naval Research, $277,879, 1990-1993

A Probabilistic Approach to Natural Language Understanding (PI), National Science Foundation, $180,000, 1989-1992

Language Comprehension (PI), Office of Naval Research, $171,895, 1988-1990

Multiparadigm Design Environments (PI), National Science Foundation, $3,504,831, 1988-1993

A Single-Semantic-Process Theory of Parsing (PI), National Science Foundation, $295,240, 1986-1989

An Approach to Abductive Inference in Artificial Intelligence Systems (PI), National Science Foundation, $120,818, 1985-1987

Digital Design Understanding as Motivation Comprehension (PI), ITT, $49,600, 1983-1986

Ideographics (Co-PI), Defense Advanced Research Projects Agency (DARPA)-Office of Naval Research (ONR), $1,700,000, 1983 - 1987

Research on Natural Language Processing (Frame Selection) (PI), National Science Foundation, $131,920, 1981-1984

Automated Technical Documentation and Assistance (Co-PI), Office of Naval Research, $891,084, 1980-1985

The Computer Solution of Word Problems in Inventory Control as a First Step Toward a Program Which Learns from Textbooks (PI), Office of Naval Research, $464,626, 1979-1988

Computer Science and Computer Engineering Research Equipment (PI), National Science Foundation, $55,096, 1979 - 1980

Computer Science and Computer Engineering Research Equipment (PI), National Science Foundation, $55,096, 1979-1980