News & Events
Topic: CTL Seminar [4:30pm 12/12/2005]: "Chinese Main Verb Identification: From Specification to Realization" by Prof. HUANG Changning
Posted - 08/12/2005 : 12:23:22
Dr. Liu Feng-hsi
City University of Hong Kong
Department of Chinese, Translation and Linguistics
Chinese Main Verb Identification: From Specification to Realization
Professor HUANG Changning
Microsoft Research Asia (MSRA)
Date: 12 December 2005, Monday
Time: 4:30pm - 5:30pm
Venue: B7603(Lift3, 7/F Blue Zone),Academic Building,CityU of Hong Kong
Main verb identification is a fundamental task in natural language processing to automatically identify the predicate-verb in an input sentence. It is particularly useful for many applications in Chinese language processing. Most previous studies focused on developing a computational model for identifying the main verbs. However, the definition of main verb should not be overlooked. In our studies to work out a sound specification design, we have found many complicated issues that require more effort than we thought before for a thorough study. We first work on the specification for annotating the main verbs, with special attention to handle those complicated cases, and then we propose an approach to identifying the main verbs by virtue of utilizing chunk information. This approach gives better results than the approach utilizing only part-of-speech information. Finally, the local contextual features are integrated into a Support Vector Machine (SVM) model. This model achieves a promising F score of 92.8%, and can be applied to improve the performance of a Chinese Sentence Breaker by 2.4%.
About the Speaker
Professor HUANG Changning (B.S.) graduated from Department of Automatic Control, Tsinghua University, China, in 1961. He joined Microsoft Research Asia (MSRA) in April 1999 as a Senior Researcher and the founding Research Manager of the NLC group. Before that he was professor in the Department of Computer Science and Technology, Tsinghua University, and the founding Director of the NLP research group in Tsinghua from 1982 to 1999. Now he is a Senior Consultant of MSRA since February 2004. Prof. Huang was the co-founder of the Computational Linguistics Committee of the Chinese Information Processing Society of China, and acted as its chair from 1992 to 2001. He has served as a Steering Committee Member for ACL-SIGDAT. He is the Editor-in-Chief of the Journal of Chinese Information Processing (in Chinese) since 1998, the Associate Editor of ACM-TALIP from its beginning. He has also served on the editorial boards of several international and national journals, and as program chair/co-chair of various academic conferences. His research interests include NLP and Chinese information processing, in particular, Chinese word segmentation, POS tagging, named entity recognition, word sense disambiguation, coreference, shallow parsing and machine translation.
~All Are Welcome~