|
|
|
SHUBIN ZHAO |
|
76 Garden Ave,
Chatham, NJ 07928 |
Phone: (917) 250-6302
E-mail: shubin@gmail.com |
|
|
|
|
Skills |
|
|
Proficient: C++, Java, Python, Perl
Familiar: Javascript, Unix Shell, etc.
|
|
|
Education |
|
|
Ph.D. in Computer Science, May 2005
New York University, New York, NY
Thesis: Information Extraction from Multiple Syntactic Sources
M.S. in Pattern Recognition and Intelligent System, June 1999
Institute of Automation, Chinese Academy of Sciences, Beijing
B.S. in Mathematics, June 1996
Department of Mathematics, Beijing University |
|
|
|
Professional Experience |
|
|
- Software Engineer, Google Inc. New York, 01/2005 - present
Improving the high performance search infrastructure (C++). 2011-present
Implemented fast text search (Java) using Google Infrastructure over data stored in MySQL. Integrated product inventory management with GoogleBase. 2008-2011
C++ development of various components of the Google online question answering system. Designed and developed large scale data mining algorithms to extract structured data from web pages. Experimented different approaches to improve related search. 2005-2008
- Summer Intern, Google Inc. New York, 06/2004 - 08/2004
Developed and implemented a query-based bootstrapping system which takes a set of entity facts as seed and find new facts and new HTML patterns simultaneously. The system is based on Google's distributed search infrastructure.
- Research Assistant, Computer Science Department, NYU, New York, 09/2002 - 12/2004
Researching on statistical learning for Information Extraction and its component technologies. Topics of interest include named entity detection, event detection, entity relation recognition, etc. Leading researcher in building the Proteus Chinese EDT(Entity Detection and Tracking) System.
- Summer Intern, Desktop News Inc. New York, 05/2000 - 08/2000
C++ development of a customizable desktop ticker that delivers news and information updates from selected web sites to desktops. Analyzed and improved application performance and system resource utilization. Designed and implemented a compact self-extractable installer.
- Research Assistant, National Laboratory of Pattern Recognition, Beijing, China, 09/1996 - 07/1999
Researched on robust parsing algorithm for spoken Chinese on ASR input.
Implemented a real-time parser that was integrated in LodeStar voice
information query system and a speech-to-speech translation system.
Developed Assembly source code of a stand-alone speech recognition card.
| |
|
|
Patents |
|
|
"Corroborating Facts in Electronic Documents".
Shubin Zhao and Krzysztof Czuba
September 2006
"Determining Document Subject by Using Title and Anchor Text of Related Documents ".
Shubin Zhao
March 2006
"Unsupervised Extraction of Facts".
Shubin Zhao and Jonathan T. Betz
March, 2006
"Learning Facts from Semi-Structured Text".
Shubin Zhao and Jonathan T. Betz
May, 2005
|
|
|
|
Publications |
|
|
"Corroborate and Learn Facts from the Web".
Shubin Zhao and Jonathan Betz
In the Proceedings of the Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Jose, CA, 2007
"Extracting Relations with Integrated Information Using Kernel Methods".
Shubin Zhao and Ralph Grishman
In the Proceedings of the 43rd Annual Meeting of Association of Computational Linguistics. 2005; Ann Arbor, Michigan.
"Discriminative Slot Detection Using Kernel Methods".
Shubin Zhao, Adam Meyers, Ralph Grishman.
In the Proceedings of the 20th International Conference on Computational Linguistics (COLING-04); Geneva, Switzerland.
"Parsing and GLARFing".
Adam Meyers, Michiko Kosaka, Satoshi Sekine, Ralph Grishman and Shubin Zhao.
In the Proceedings of the EuroConference of Recent Advances in NLP
(RANLP 2001)
"Covering Treebanks With GLARF".
Adam Meyers, Ralph Grishman, Michiko Kosaka and Shubin Zhao.
In the Proceedings of the ACL Workshop on Sharing Tools and Resources, 2001
"LODESTAR: A Mandarin Spoken Dialogue System for Travel Information
Retrieval".
Chao HUANG, Peng XU, Xin ZHANG, Shubin ZHAO, Taiyi HUANG and Bo XU.
EUROSPEECH 1999
|
|
|
|
|
Reference |
Available upon request |
|