Regina Barzilay
Associate Professor, EECS
Ross Career Development Professor
Microsoft Faculty Fellow
MIT Computer Science & Artificial Intelligence Lab
32 Vassar Street, 32-G468
Cambridge, MA 02139
(617) 258-5706
regina@csail.mit.edu
Research
My interests lie in the area of natural language processing. My research has two dominant themes: (1) developing new probabilistic techniques that automatically infer accurate models of natural language phenomena; (2) building scalable, robust systems that use these models to solve complex real-world language processing tasks. Current projects include:
- Modeling Document-Level Structure (EMNLP 2008a , JAIR 2009c , ACL 2009c )
- Unsupervised Multilingual Learning and Decipherment of Ancient Scripts (ACL 2008a, JAIR 2009b, ACL 2009a)
- Imperative Language Grounding ( ACL 2009b )
Papers
Code
Systems
- We released our restaurant summarization system. The system implements ideas from these papers "Multiple Aspect Ranking using the Good Grief Algorithm" (NAACL 2007) and "Learning Document-Level Semantic Properties from Free-text Annotations" (JAIR 2009)
- Check out Wikipedia articles generated by our system. For details, see "Automatically Generating Wikipedia Articles: A Structure-Aware Approach" (ACL 09)
- Our topical segmentation algorithm (ACL-06) is incorporated into the MIT Lecture Browsing and Retrieval Tool. Download the segmentor code from here .
Teaching
- Advanced Natural Language Processing [F05], [F06], [F08], [F09]
- Artificial Intelligence[S08], [S09]
- Computational Models of Discourse [S04]
- Structure and Interpretation of Computer Programs (Recitations) [F03], [S05], [S06]
Students
Theses by my students
Selected Professional Activities
- Associate Editor, Journal of Artificial Intelligence Research , 2009-2012
- Executive Board, the North American Chapter of the Association for Computational Linguistics (NAACL), 2006-2007
- Editorial Board, Computational Linguistics , 2005-2007
- Organizer, CSAIL LLVG seminar series , 2004-2008