Boxing CHEN 

 

Senior Research Fellow

Institute for Infocomm Research
21-01 Connexis
1 Fusionopolis Way
Singapore 138632
Tel:
Fax:
Email:

(65) 6408 2769
(65) 6776 6792
bxchen (AT) i2r.a-star.edu.sg
 
 
Boxing Chen was a Senior Research Fellow in the Department of Human Language Technology (HLT), Institute for Infocomm Research (I2R), A*STAR, Singapore from April 2007 to Feb. 2009. His research interests include Machine Translation, Statistical Natural Language Processing and Computational Linguistics.

Soon after joining I2R in April 2007, he contributed immensely to I2R's effort in the IWSLT-2007 competition, which produced the 1st place in the Chinese-English task out of 15 participants, and won the second position by more than 3 Bleu-score.

Before joining I2R, he was a postdoc in the HERMES research group (Cross-Language Information Processing), SSI Division, of ITC-IRST. He was responsible for the work on the IWSLT-2005 competition. This led to an improvement in Bleu-score of 12 points and has allowed IRST to move from the 5th place in 2004 to the 1st place in 2005. IRST's system achieved the top position for 3 out of the 4 languages entered in the competition.

Here is his CV. To know more about his personal infomation, please click the picture on the top-left.

EDUCATION
  • July 2003            
Ph.D. Degree
 Natural Language Processing
Institute of Acoustics, Chinese Academy of Sciences, Beijing, China
Dissertation:
Knowledge Acquisition and Machine Translation Based on Bilingual Spoken Language Corpora
  • July 1998
B.Sc. Degree
Signal and Information Processing
Electronics Department, Peking University, Beijing, China
Thesis:  
Chinese Characters Display and Speech Synthesis System Based on SCM
 

PROFESSIONAL EXPERIENCE
  • Apr. 2007 ~ Feb. 2009           
Senior Research Fellow
Department of Human Language Technology (HLT), Institute for Infocomm Research (I2R), A-STAR, Singapore
  • Jan. 2005 ~ Mar. 2007
Postdoctoral Fellow
HERMES, Institute for Scientific and Technological Research, ITC-IRST (FBK-IT), Trento, Italy
  • Sep. 2003 ~ Dec. 2004
Postdoctoral Fellow
LIDILEM, University of Grenoble 3, Grenoble, France
  • Sep. 1998 ~ Jul. 2003
Research Assistant
Institute of Acoustics, Chinese Academy of Sciences, Beijing, China
  • Sep. 1997 ~ Jul. 1998
Research Assistant
Electronics Department, Peking University, Beijing, China

PROJECTS RECORD

  • TC-STAR Project
    o Jan. 2005- Mar. 2007
    Phrase-based Statistical Machine Translation.
  • CARMEL Project
    o Sep. 2003-Dec. 2004 
    Word Alignment and Word Sense Disambiguation Based on Multilingual Parallel Corpora.
  • Sub-Project "The Research of the Platform for Chinese Spoken Dialogue System." of the 973 National Key Fundamental Research Project of China.
  • CAS-AT&T International Collaborate Five-Year Plan "Chinese-English Speech Translation" Research Project, Machine Translation Research Group of CAS. Took charge of the Machine Translation group.
    o Jan. 2001-Jul. 2003 

    Combination of Template-Driven Example-Based and Statistical Machine Translation.
    o Jan. 2000-Dec.2000
    Automatic Extraction of Translation Lexicon Based on Parallel Corpora and Language Modelling.
    o Jan. 1999-Dec.1999
     Pattern Based Machine Translation Based on Control Language.
  • "Mimi Pinyin Bao" Development Project; took charge of the group.
    o Sep. 1997-Jun. 1998
    Chinese Characters Display and Speech Synthesis System Based on SCM.

PUBLICATIONS
  • Boxing Chen, Min Zhang and Aiti Aw. Two-pass Hypotheses Generation for Spoken Language Translation. To appear in ACM Transactions on Asia Language Information Processing. (PDF)
  • Boxing Chen, Deyi Xiong, Min Zhang, Aiti Aw, Haizhou Li. 2008. I2R Multi-Pass Machine Translation System for IWSLT 2008. In: Proceeding of IWSLT 2008. pp.46-51. Oct. Hawaii, US. (PDF) (SLIDES)
  • Maxim Khalilov, Marta R. Costa-jussà, Carlos A. Henríquez, José A. R. Fonollosa, Adolfo Hernández, José B. Mariño, Rafael E. Banchs, Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li. 2008. The TALP & I2R SMT Systems for IWSLT 2008. In: Proceeding of IWSLT 2008. pp.116-123. Oct. Hawaii, US. (PDF)
  • Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li. 2008. Regenerating Hypotheses for Statistical Machine Translation. In: Proceeding of COLING 2008. pp105-112. Manchester, UK. Aug. (PDF) (SLIDES)
  • Boxing Chen, Min Zhang, Aiti Aw and Haizhou Li. 2008. Exploiting N-best Hypotheses for SMT Self-Enhancement. In: Proceeding of ACL-2008: HLT. Ohio, US. June. (PDF) (SLIDES)
  • Boxing Chen, Jun Sun, Hongfei Jiang, Min Zhang and Aiti Aw. 2007. I2R Chinese-English Translation System for IWSLT-2007. In: Proceeding of IWSLT 2007. pp. 55-60. Oct. Trento, Italy. (PDF) (SLIDES)
  • D. Falavigna, N. Bertoldi, F. Brugnara, R. Cattoni, M. Cettolo, B. Chen, M. Federico, D. Giuliani, R. Gretter, D. Gupta and D. Seppi. 2007. The IRST English-Spanish Translation System for European Parliament Speeches. In: Proceeding of Interspeech. August, Antwerp, Belgium. (PDF)
  • Boxing Chen, Marcello Federico and Mauro Cettolo. 2007. Better N-best Translations through Generative n-gram Language Models. In: Proceeding of MT Summit XI. September, Copenhagen, Denmark. (PDF) (SLIDES)
  • Boxing Chen, R. Cattoni, N. Bertoldi, M. Cettolo, and M. Federico. 2006. The ITC-irst SMT System for IWSLT-2006. In: Proceeding of IWSLT 2006, pp. 182-189. Nov. Kyoto, Japan. (PDF) (SLIDES)
  • Boxing Chen, Mauro Cettolo and Marcello Federico. 2006. Reordering Rules for Phrase-based Statistical Machine Translation. In: Proceeding of IWSLT 2006, pp 53-58. Nov. Kyoto, Japan. (PDF) (SLIDES)
  • R. Cattoni, N. Bertoldi, M. Cettolo, B. Chen and M. Federico. 2006. A Web-based Interface to a Multi-lingual Phrase-based Translation System. In: Systems Demonstrations of the ECAI 2006, Riva del Garda, Italy. August. (PDF)
  • Boxing Chen, Marcello Federico. 2006. Improving Phrase-Based Statistical Translation through Combination of Word Alignment. In: Proceedings of FinTAL2006. pp 356-367. August 23-25. Turku, Finland. (PDF) (SLIDES)
  • N. Bertoldi, M. Cettolo, R. Cattoni, B. Chen and M. Federico. 2006. ITC-irst at the 2006 TC-STAR SLT Evaluation Campaign. In: Proceedings of TC-STAR Workshop, pp 18-24. June. Barcelona, Spain. (PDF)
  • R. Cattoni, N. Bertoldi, M. Cettolo, B. Chen and M. Federico. 2006. A Web-based Demonstrator of a Multi-lingual Phrase-based Translation System. In: Proceedings of Conference Companion of the EACL 2006, Trento, Italy. (PDF)
  • M. Federico, N. Bertoldi, R. Cattoni, M. Cettolo, B. Chen and D. Gupta. 2005. Traduzione Automatica di Sessioni del Parlamento Europeo. In: Associazione Italiana di Scienze della Voce, Nov. Italy. (In Italian) (PDF)
  • Boxing Chen, R. Cattoni, N. Bertoldi, M. Cettolo, and M. Federico. 2005. The ITC-irst SMT System for IWSLT-2005. In: Proceeding of IWSLT 2005, Oct. Pittsburgh, USA. (PDF) (SLIDES)
  • M. Cettolo, M. Federico, N. Bertoldi, R. Cattoni and B. Chen. 2005. A Look inside the ITC-irst SMT System. In: Proceeding of MT Summit X, Sep. Phuket, Thailand. (PDF)
  • Chen B., El-Bèze M., Haddara M., Kraif O., Moreau de Montcheuil G. 2005. Contextes multilingues alignés pour la désambiguïsation sémantique : une étude expérimentale. In: Actes de TALN-RECITAL 2005. 6-10 juin, Dourdan, vol. 1, pp. 415-420. (In French) (PDF)
  • Moreau de Montcheuil G., Chen B., El-Bèze M., Kraif O. 2004. Using a Word Sense Disambiguation system for translation disambiguation: the LIA-LIDILEM team experiment. In: Proceedings of Senseval3 Workshop, Barcelona, July, pp. 175-178. (PDF)
  • Olivier Kraif, Boxing Chen. 2004. Combining clues for lexical level aligning using the Null hypothesis approach. In: Proceedings of Coling 2004, Geneva, August, pp. 1261-1264. (PDF)
  • Du, Limin, Chen, Boxing. 2003. Automatic extraction of bilingual chunk lexicon for spoken language translation, In: Proceedings of EUROSPEECH-2003, September 1-4, pp. 2333-2336, Geneva, Switzerland. (Abstract)
  • Chen, Boxing & Du, Limin. 2003. Preparatory Work on Automatic Extraction Bilingual Multi-Word Units from Parallel Corpora. Computational Linguistics & Chinese Language Processing. Vol. 8, No. 2, August, pp. 77-92. (PDF)
  • Chen, Boxing & Du, Limin. 2003. Extraction of Machine Translation Units Based on "Similarity and Difference". Journal of Chinese Information, 17(3) pp. 34~40, (In Chinese)
  • Chen, Boxing & Du, Limin. 2002. Automatic Construction of English-Chinese Translation Lexicon from Parallel Spoken Language Corpus. In: Proceedings of ISCSLP2002, Taipei, August, pp.205~210.
  • Chen, Boxing & Du, Limin. 2002. Alignment of Single Source Words and Target Multi-word Units from Parallel Corpus. In: First Student Workshop on Computational Linguistics, Beijing, pp.318-327. (In Chinese) (Honored as Excellent Paper, and published in Journal of Chinese Information, 17(1), pp.13~19).
  • Chen, Boxing & Du, Limin. 2002. Automatically Extract English-Chinese Translation Lexicon from Bilingual Parallel Corpora. In: The Chinese Journal of Computers, 26(3) pp. 275~280. (In Chinese)

LANGUAGES
  • Chinese
  • English
  • French
  • Italian
 (Native)
(Fluent)
(Basic)
(Basic)

------ HLT <-- I2R <-- A*STAR <-- Singapore --------
 
@ Latest Update: Oct. 2008 @
Disclaimer: The Institute for Infocomm Research is not responsible for any contents found on this homepage or any opinion expressed herein.