Joyce Chai

Joyce Chai received her Ph.D degree from Computer Science Department at Duke University in December, 1998. Her dissertation proposed a new information extraction paradigm - a trainable information extraction system. It allows any casual user to train the system on different domains. Then the system will automatically create both syntactically and semantically generalized rules to capture the target information. From 1994-1998, she was awarded an IBM Fellowship for her graduate study.

Joyce Chai's research interests include information extraction, information retrieval, natural language processing, human computer interaction, machine learning and dialog systems. Currently, she is doing research on integrating techniques in natural language processing, human computer interaction and information retrieval for e-commerce.

Selected Publications

• Information Extraction from Free Text, A. Bagga, J. Y. Chai and A. W. Biermann, invited chapter to book Computing with Word, Forthcoming, 1999.
• The Use of Word Sense Disambiguation in an Information Extraction System, J. Chai and A. W. Biermann, in Proceedings of Eleventh Annual Conference on Innocative Applications of Artificial Intelligence (IAAI-99), pp. 850-855, July, 1999.
• Two Dimensional Rule Generalization for Information Extraction, J. Y. Chai, A. W. Biermann and C. I. Guinn, in Proceedings of Sixteenth National Conference in Artificial Intelligence (AAAI'99), pp. 431-438, July, 1999.
• Learning and Generalization in the Creation of Information Extraction Systems, J. Y. Chai, Ph.D Dissertation, Computer Science Department, Duke University, December, 1998.
• Corpus Based Statistical Generalization Tree in Rule Optimization, J. Y. Chai and A. W. Biermann, in Proceedings of Fifth Workshop on Very Large Corpora (WVLC-5), pp. 81-90, August, 1997.
• A WordNet Based Rule Generalization Engine For Meaning Extraction, J. Y. Chai and A. W. Biermann, in Lecture Notes in Artificial Intelligence (1325): Foundations of Intelligent Systems, pp. 529-539, Springer-Verlag, 1997. Presented at Tenth International Symposium On Methodologies For Intelligent Systems (ISMIS97)
• The Role of WordNet in the Creation of a Trainable Message Understanding System, A. Bagga, J. Y. Chai and A. W. Biermann, in Proceedings of The Fourteenth National Conference on Artificial Intelligence and the Ninth Conference on the Innovative Applications of Artificial Intelligence (AAAI/IAAI'97), pp. 941-948, August, 1997.
• The Use of Lexical Semantics in Information Extraction, J. Y. Chai and A. W. Biermann, in Proceedings of ACL Workshop on Automatic Information Extraction and Build ing of Lexical Semantic Resources for NLP Applications, pp. 61-70, July, 1997.
• Trainable System for Extracting Meaning from Text, A. Bagga and J. Y. Chai, in Computational Natural Language Learning (CONLL97), pp. 1-8, July, 1997.
• A Trainable System for the Extraction of Meaning From Text , A. Bagga and J. Y. Chai, demo presented at the Fifth Conference on Applied Natural Language Processing (ANLP'97), Descriptions of System Demonstrations and Videos}, pp. 7-8, Washington. DC, 1997.