Natural language research announcements

["Alexandre Klementiev" <klementi AT uiuc.edu>]

Dear faculty and students,

Prof. Regina Barzilay   will give a talk (details below) at the AIIS seminar next Thursday. 

As I am in the process of aggregating relevant newsgroups for
advertising upcoming AIIS talks, I apologize for multiple announcements which you may receive for this talk. 

Thank you,
Alex

Title: Statistical Models of Discourse Structure


Speaker: 


Regina Barzilay, 
MIT Computer Science & Artificial Intelligence Lab


Date: Nov. 8, 4:30pm
Location:    Siebel 4405




Abstract:
Bag-of-words representations are used in many NLP applications, such as text


 classification and sentiment analysis. These representations ignore relations across different sentences in a text and disregard the underlying structure of


 documents. While more linguistically elaborate models of text structure have been studied for decades, they are rarely used in text analysis applications. A
 reliance on handcrafted rules combined with the limited portability and scalability of these models makes bag-of-words approaches the representation of
 choice in practical settings.



In this talk, I will demonstrate that incorporating structural information in document analysis yields significant performance gains over bag-of-words


 approaches. First, I will describe how models of text structure can be learned from a collection of unannotated texts, bypassing the need for complex


 annotations. The key premise of our work is that by analyzing patterns in word distribution we can predict high-level patterns in discourse organization.


 Second, I will show how these models can be effectively integrated into core text processing applications such as topical classification and sentiment


 analysis.

This is joint work with Amir Globerson, Zoran Dzunic, Yoong Keok Lee, Igor
    Malioutov and Benjamin Snyder.


Bio:
Regina Barzilay is an associate professor in the Department of Electrical


 Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory at MIT. Her main research area is natural
 language processing.  She obtained her PhD from Columbia University in 2003, and she was a postdoc at Cornell University in 2003-2004. Her honors include an
 NSF CAREER Award (2004) and Microsoft Faculty Fellowship (2006).  In 2005 she was named one of Technology Review Magazine's TR35 for being a top young
 innovator of the twenty-first century.