Wei Wang
Language Weaver, Inc., 4640 Admiralty way, suite 1210, Marina Del Rey, CA 90292, email wwang AT languageweaver DOT com
I am a research scientist at Language Weaver, Inc. I was a research scientist at Computer Science Department, Courant Institute of Mathimatical Sciences, New York University.
Research interests include: stochastic syntax-based machine translation, machine learning, heuristic searching, parsing.
SELECTED PUBLICATIONS
2007
"Binarizing Syntax Trees to Improve Syntax-Based Machine Translation Accuracy", Wei Wang, Kevin Knight and Daniel Marcu (2006). EMNLP-2007.
"What Can Syntax-Based MT Can Learn from Phrase-Based MT?", Steve DeNeefe, Kevin Knight, Wei Wang, Daniel Marcu (2007). EMNLP-2007.
2006
"SPMT: Statistical Machine Translation with Syntactified Target Language Phrases", Daniel Marcu, Wei Wang, Abdessamad Echihabi, and Kevin Knight (2006). EMNLP-2006.
"Scalable Inferences and Training of Context-Rich Syntax Translation Models", Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, and Ignacio Thayer (2006). ACL-2006.
"Capitalizing Machine Translation", Wei Wang, Kevin Knight and Daniel Marcu. in Proc. NAACL-HLT, 2006.
2005
"Design and Implementation of a Generalized Parser", I. Dan Melamed and Wei Wang, this is the documentation of the GenPar, and was used as an initial draft of a section of the final report of the "statistical machine translation by parsing" project at JHU 2005 summer workshop, 2005.
2004
"Improving Word Alignment Models Using Structured Monolingual Corpora", Wei Wang and Ming Zhou, in Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-04), Barcelona, Spain, 2004 .
"Statistical Machine Translation by Parsing", I. Dan Melamed and Wei Wang. Also submitted for publication to CL journal, 2004.
2003
"A Unified Statistical Model for Generalized Translation Memory System", Jin-Xia Huang, Wei Wang and Ming Zhou, In Proceedings of Machine Translation Summit IX, 2003, New Orleans , Louisiana, USA, 2003.
"Factorization of Language Models through Backing-Off Lattices", Wei Wang, The Computing Research Repository (CoRR), May 2003.
2002
"Structure Alignment Using Bilingual Chunking", Wei Wang, Ming Zhou and Jin-Xia Huang, In Proceedings of the 19th International Conference on Computational Linguistics (COLING-02), Taipei, Taiwan, 2002.
2001
"Finding Target Language Correspondence for Lexicalized Example-Based Machine Translation System", Wei Wang, Jin-Xia Huang and Ming Zhou, In Proceedings of the Sixth Natural Language Processing Pacific Rim Symposium (NLPRS-01), Tokyo, Japan, 2001.
PATENT
Example based machine translation system (United States Patent 20040002848)