Domain Adaptation for Text Information Management
by Jing JIANG

Abstract

With the explosion of the amount of textual data in the information age, text information management techniques have become increasingly important. A common and effective approach to solving many text analysis problems such as text categorization, spam filtering, entity recognition, and relation extraction is supervised machine learning. However, standard supervised learning requires the labeled training corpus to be similar to the unlabeled test corpus, and therefore falls apart in real applications because obtaining labeled text for every new domain is expensive and thus infeasible. In this talk, I will present the major line of my PhD research on domain adaptation in natural language processing, which aims at adapting classifiers trained on one domain to another domain. We have developed two general frameworks to achieve domain adaptation, both having been evaluated on real text analysis problems and outperformed standard baseline methods. I will also mention my future plans along this direction with applications in Web text mining and scientific literature mining.

About the speaker

Jing Jiang is a final year PhD student in the Text Information Management Group in the Department of Computer Science at the University of Illinois at Urbana-Champaign, working with Professor ChengXiang Zhai. Her research interests include information extraction, information retrieval, natural language processing, text mining, and machine learning. She received her B.S. degree and her M.S. degree in Computer Science from Stanford University in 2002 and 2003, respectively.