Tong XIAO Resume
XIAO, Tong Tel: +86-24-836*****
Post-doctor researcher Fax: +86-24-836*****
Institute of Computer Software Email: abqj0j@r.postjobfree.com
College of Information Science & Engineering Web: http://www.nlplab.com/members/~xiaotong.html
Northeastern University
Shenyang, P.R.China.
Postal Code: 110819
Education Ph.D. in Computer Science 09/2008 - 07/2012
Advisor: Dr. Jingbo Zhu
External co-advisor: Dr. Keh-Yih Su
Natural Language Processing Lab
Northeastern University, Shenyang, China
M.S. in Computer Science 09/2005 - 03/2008
Supervisor: Dr. Li Zhang
Natural Language Processing Lab
Northeastern University, Shenyang, China
B.S. in Computer Science 09/2001 - 07/2005
Northeastern University, Shenyang, China
Research Interests Natural Language Processing:
- Machine Translation (My recent work has been focused on syntax-based MT, in particular
the approaches/models that make use of the syntax of both source and target languages)
- Syntactic Alignment
- Language Modeling
Experience Post-doctor researcher 07/2012 - Now
Natural Language Processing Lab, Northeastern University, Shenyang, China
Working on Syntax-based and semantics-augmented machine translation
Ph.D. Candidate 09/2008 - 07/2012
Natural Language Processing Lab, Northeastern University, Shenyang, China
Working on Training and Decoding for Tree-to-tree Translation
Research Intern 08/2008 - 07/2009
Microsoft Research Asia, Bejing, China
Mentor: Dr. Mu Li
Working on Better Synchronous Binarization for Machine Translation
Visiting Fellowship 09/2006 - 09/2007
Fuji Xerox, Hadano, Japan
Working on Chinese Chunking and Example-based Approaches to Chinese-Japanese Ma-
chine Translation
Master 09/2005 - 03/2008
Natural Language Processing Lab, Northeastern University, Shenyang, China
Working on Comparison of Word-based and Phrase-based Approaches to Machine Transla-
tion .
1
Tong XIAO Resume
Projects Co-Principle Investigator and Core Developer 09/2009 - Present
Experience NiuTrans Open Source Project (http://www.nlplab.com/NiuPlan/NiuTrans.html)
Principle Investigator 01/2010 - 12/2011
Project: Towards Better Use of Tree Structure for Machine Translation
Funded by the Ministry of Education of the People s Republic of China
Core Developer 09/2010 - 03/2012
Project: CIIPS Patent Processing Platform
Cooperated with CIIPS R&D (U.S.)
Architecture and Global Design
Core Developer 03/2008 - 07/2008
Project: Chinese Geographic Information System
Cooperated with NEUSOFT R&D (China)
Core Developer 08/2005 - 09/2007
Project: Sport-domain Chinese-Japanese Example-based Machine Translation System
Cooperated with Fuji Xerox (Japan)
Professional PC members of IJCNLP2011, SWCL2010, SEWM2009 and SWCL2008
Activities Reviewer for Journal of the Acoustical Society of America (2011-2012)
Reviewer for International Journal of Pattern Recognition and Arti cial Intelligence (2007-
2008)
Reviewer for International Journal of Computational Linguistics and Chinese Language Pro-
cessing (2007-2012)
Reviewer for International Journal of Computer Processing Of Languages (2010-2012)
Secondary Reviewers for EACL2012, EMNLP2012 and AAAI2011
Honors and Excellent Paper Award of The 5th National Young Workshop on Computational Linguistics,
Awards 2010
Excellent Paper Award of The 10th Chinese National Conference on Computational Lin-
guistics, 2009
Excellent Master Thesis Award of Northeastern University, 2008
Excellent Undergraduate Student Fellowship, Northeastern University, 2001-2005
Evaluation Tasks [1] NTCIR-9 Chinese-English Patent MT Track - 2nd place (human evaluation)
Tong Xiao, Qiang Li, Qi Lu, Hao Zhang, Haibo Ding, Shujie Yao, Xiaoming Xu, Xiaoxu
Fei, Jingbo Zhu, Feiliang Ren and Huizhen Wang. 2011. The NiuTrans Machine Translation
System for NTCIR-9. In Proc. of NTCIR-9 Workshop Meeting, Tokyo, Japan, pages 593-599.
[2] CWMT2011 English-Chinese/Chinese-English News-Domain MT Tracks -
1st and 4th places (BLEU)
Tong Xiao, Hao Zhang, Qiang Li, Qi Lu, Jingbo Zhu, Feiliang Ren and Huizhen Wang.
2011. The NiuTrans Machine Translation System for CWMT2011. In Proc. of The 6th
China workshop on Machine Translation (CWMT), Xiamen, China.
[3] CWMT2009 Chinese-English Single System Track - 2nd place (BLEU)
Tong Xiao, Rushan Chen, Tianning Li, Muhua Zhu, Jingbo Zhu, Huizhen Wang and Feiliang
Ren. 2009. NEUTrans: a Phrase-Based SMT System for CWMT2009. In Proc. of The 5th
China workshop on Machine Translation (CWMT), Nanjing, China.
2
Tong XIAO Resume
[4] NTCIR-7 English Patent Mining Track - 1st place (MAP)
Tong Xiao, Feifei Cao, Tianning Li, Guolong Song, Ke Zhou, Jingbo Zhu and Huizhen Wang.
2008. KNN and Re-ranking Models for English Patent Mining at NTCIR-7. In Proc. of
NTCIR-7 Workshop Meeting, Tokyo, Japan, pages 333-340.
Publications [1] Tong Xiao, Jingbo Zhu and Tongran Liu. Bagging and Boosting Statistical Machine Trans-
(selected) lation Systems. To appear in Arti cial Intelligence Journal.
[2] Ji Ma, Tong Xiao, Jingbo Zhu, and Feiliang Ren. 2012. Easy-First Chinese POS Tagging
and Dependency Parsing. In Proc. of the 24rd International Conference on Computational
Linguistics (COLING), Jeju, Korea.
[3] Tong Xiao, Jingbo Zhu, Hao Zhang and Qiang Li. 2012. NiuTrans: An Open Source Toolkit
for Phrase-based and Syntax-based Machine Translation. In Proc. of the 50th Annual Meet-
ing of the Association for Computational Linguistics (ACL, system demonstration), Jeju,
Korea, pages 19-24.
[4] Jingbo Zhu, Tong Xiao and Chunliang Zhang. 2012. Learning Better Rule Extraction with
Translation Span Alignment. In Proc. of the 50th Annual Meeting of the Association for
Computational Linguistics (ACL, short paper), Jeju, Korea, pages 280-284.
[5] Tong Xiao, Jingbo Zhu and Shujie Yao. 2011. Document-level Consistency Veri cation in
Machine Translation. In Proc. of MT summit XIII, Xiamen, China, pages 131-138.
[6] Jingbo Zhu and Tong Xiao. 2011. Improving Decoding Generalization for Tree-to-String
Translation. In Proc. of the 49th Annual Meeting of the Association for Computational
Linguistics (ACL, short paper), Portland, USA, pages 418-423.
[7] Tong Xiao, Jingbo Zhu and Muhua Zhu. 2011. Language Modeling for Syntax-based Machine
Translation Using Tree Substitution Grammars: A Case Study on Chinese-English Transla-
tion. ACM Transactions on Asian Language Information Processing (TALIP), 10(4):1-29.
[8] Muhua Zhu, Jingbo Zhu and Tong Xiao. 2011. Automatic Treebank Conversion via Informed
Decoding - A Case Study on Chinese Treebanks. ACM Transactions on Asian Language In-
formation Processing (TALIP), 10(3):1-23.
[9] Tong Xiao, Jingbo Zhu, Muhua Zhu and Huizhen Wang. 2010. Boosting-based System Com-
bination for Machine Translation. In Proc. of the 48th Annual Meeting of the Association
for Computational Linguistics (ACL), Uppsala, Sweden, pages 739-748.
[10] Tong Xiao, Jingbo Zhu, Hao Zhang and Muhua Zhu. 2010. An Empirical Study of Transla-
tion Rule Extraction with Multiple Parsers. In Proc. of the 23rd International Conference
on Computational Linguistics (COLING, poster session), Beijing, China.
[11] Muhua Zhu, Jingbo Zhu and Tong Xiao. 2010. Heterogeneous Parsing via Collaborative
Decoding. In Proc. of the 23rd International Conference on Computational Linguistics
(COLING), Beijing, China.
[12] Tong Xiao, Mu Li, Dongdong Zhang, Jingbo Zhu and Ming Zhou. 2009. Better Synchronous
Binarization for Machine Translation. In Proc. of the 2009 Conference on Empirical Meth-
ods in Natural Language Processing (EMNLP), Singapore, pages: 362-370.
3
Tong XIAO Resume
[13] Nan Duan, Mu Li, Tong Xiao and Ming Zhou. 2009. The Feature Subspace Method for SMT
System Combination. In Proc. of the 2009 Conference on Empirical Methods in Natural
Language Processing (EMNLP), Singapore, pages 1096-1104.
[14] Shujie Yao, Tong Xiao and Jingbo Zhu. 2010. Selection of SMT Training Data Based on
Sentence Pair Quality and Coverage. In Proc. of The 5th National Young Workshop on
Computational Linguistics, China, pages 221-227 (In Chinese. Excellent Paper Award).
[15] Hao Zhang, Huizhen Wang, Tong Xiao and Jingbo Zhu. 2010. The impact of parsing accu-
racy on syntax-based SMT. In Proc. of IEEE NLPKE 2010, Beijing, China.
[16] Tong Xiao, Tianning Li, Rushan Chen, Jingbo Zhu and Huizhen Wang. 2009. Word Re-
alignment for Statistical Machine Translation. In Proc. of The 10th Chinese National Con-
ference on Computational Linguistics, China, pages 439-445 (In Chinese. Excellent Paper
Award).
Papers in [1] Tong Xiao, Jingbo Zhu, Keh-Yih Su. Unsupervised Probabilistic Sub-tree Alignment for
Submission Tree-to-tree Translation. Submitted to a major conference.
[2] Tong Xiao, Jingbo Zhu, Keh-Yih Su. Beam-width limited and BLEU Oriented Training for
Tree-to-tree Translation. Submitted to a major conference.
Software NiuTrans open source training and decoding platform for statistical machine translation.
http://www.nlplab.com/NiuPlan/NiuTrans.html
Personal Citizen of the P. R. China.
Information Born June 1982, Shenyang, China.
Languages: Mandarin (native); English (read/write/speak); Japanese (basic conversational).
Programming Languages: C/C++, C#, Perl
References available upon request
4