Welcome to Wei-Yun Ma's Homepage!
Wei-Yun Ma
PhD Candidate
Computer Science at Columbia University
New York City, U.S.A.
wm2174@columbia.edu
¡@
¡@
I am a PhD candidate in Computer Science at Columbia University.
I work with Prof. Kathy McKeown in the Natural Language Processing Group.
¡@
My research interests include Natural Language Processing, Machine Translation,
Semantic and Knowledge Representation, Information Retrieval and Machine Learning.
[my research description]
¡@
My current research topic is "Multi-Engine Machine Translation", focusing on
fusing the outputs of MT systems based on syntactic and semantic analyses of the
source and the target language to produce a new better translation.
[related papers] [my slides]
I come from Taiwan. I received a Bachelor's degree in Computer Science and Engineering at
Yuan Ze University (YZU), and a Masters degree in Computer Science Information Engineering at
National Chiao Tung University (NCTU), where I focused on how to improve speed for
continuous speech recognition. I had interned at Industrial Technology Research Institute (ITRI) for one year to develop
speech-command-recognition 8051 chip and had worked in Chinese Knowledge Information Processing Group (CKIP)
at Institute of Information Science, Academia Sinica, participating in several Chinese NLP projects for five years.
[my CV]
Reviewer: The 2012 Conference on Computational Linguistics and Speech Processing (ROCLING 2012)
¡@
Wei-Yun Ma, Kathleen McKeown. 2012. Detecting and Correcting Syntactic Errors in Machine Translation Using
Feature-Based Lexicalized Tree Adjoining Grammars. In International Journal of Computational Linguistics
and Chinese Language Processing (IJCLCLP), Vol 17, No. 4, pp. 1-14.
¡@
Wei-Yun Ma and Keh-Jiann Chen, 2005, Design of CKIP Chinese Word Segmentation System, In International Journal of Asian Language Processing, Vol 14. No. 3. pp. 235-249.
¡@
¡@
Kristen Parton, Wei-Yun Ma, Kathleen McKeown, and James Allan. 2010. Using Query Time Information to Improve Multilingual
Search and Response Generation. In Handbook of Natural Language Processing and Machine Translation:
DARPA Global Autonomous Language Exploitation. Joseph Olive (ed.)
¡@
¡@
Wei-Yun Ma, Kathleen McKeown. 2013. Using a Supertagged Dependency Model to Select a Good Translation
in System Combination. In Proceedings of NAACL-HLT
¡@
Wei-Yun Ma, Kathleen McKeown. 2012. Phrase-level System Combination for Machine Translation Based on
Target-to-Target Decoding. In Proceedings of the 10th Biennial Conference of the Association for Machine Translation in the Americas (AMTA), San Diego, CA. [my slides]
¡@
Wei-Yun Ma, Kathleen McKeown. 2012. Detecting and Correcting Syntactic Errors in Machine Translation Using
Feature-Based Lexicalized Tree Adjoining Grammars. In Proceedings of Conference on
Computational Linguistics and Speech Processing (ROCLING) [my slides]
¡@
Wei-Yun Ma, Kathleen McKeown. 2011. System Combination for Machine Translation Based on Text-to-Text Generation In Proceedings of Machine Translation Summit XIII
¡@
Wei-Yun Ma, Kathleen McKeown. 2009. Where's the Verb Correcting Machine Translation During Question Answering In Proceedings of ACL-IJCNLP
¡@
Kristen Parton, Kathleen R. McKeown, Bob Coyne, Mona T. Diab, Ralph Grishman, Dilek Hakkani-Tür, Mary Harper, Heng Ji, Wei-Yun Ma, Adam Meyers, Sara Stolbach, Ang Sun, Gokhan Tur, Wei Xu and Sibel Yaman. 2009. Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task, In Proceedings of ACL-IJCNLP
¡@
Chu-Ren Huang, Wei-Yun Ma, Yi-Ching Wu, and Chih-Ming Chiu, 2006, Knowledge-Rich Approach to Automatic
Grammatical Information Acquisition:Enriching Chinese Sketch Engine with a Lexical Grammar, In Proceedings of the 20th Pacific Asia Conference on Language, Information and Computation.
¡@
Wei-Yun Ma and Chu-Ren Huang, 2006, The Identification of Nominalizations in
Mandarin Chinese Using Corpus-based Models (in Chinese), In Proceedings of Conference on
Computational Linguistics and Speech Processing (ROCLING).
¡@
Wei-Yun Ma and Chu-Ren Huang, 2006, Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus, In Proceedings of Language Resources and Evaluation Conference (LREC).
¡@
Keh-Jiann Chen, Wei-Yun Ma, 2002, Unknown Word Extraction for Chinese Documents, In Proceedings of COLING 2002, pp.169-175. Wei-Yun Ma, Chen Keh-Jiann, 2001, Construction and Management for Chinese Corpus (in Chinese),
In Proceedings of Conference on Computational Linguistics and Speech Processing (ROCLING), pp.175-191.
¡@
Jia-Fei Hong, Chu-Ren Huang, and Wei-Yun Ma, 2006, Corpus-based Extraction of Cross-strait
Corresponding Words (in Chinese), In Proceedings of the seventh Chinese Lexical Semantics Workshop (CLSW)
Wei-Yun Ma and Keh-Jiann Chen, 2003, A Bottom-up Merging Algorithm for Chinese Unknown Word Extraction, In Proceedings of ACL, Second SIGHAN Workshop on Chinese Language Processing, pp31-38. Wei-Yun Ma and Keh-Jiann Chen, 2003, Introduction to CKIP Chinese Word Segmentation System for
the First International Chinese Word Segmentation Bakeoff, In Proceedings of ACL, Second SIGHAN Workshop
on Chinese Language Processing, pp168-171.