Wei-Te Chen 陳維德

News

Research

Education

• Ph.D in Department of Computer Science, University of Colorado, Boulder, Colorado, U.S.A.
  • August 2010 ~ December 2017
  • Supervisor: Martha Palmer, Professor
  • Laboratory: The Center for Computational Language and EducAtion Research (CLEAR)
• M.S. in Information Systems and Applications, National Tsing Hua University, HsinChu, Taiwan
  • July 2005 ~ June 2007
  • Advisor: Jason S. Chang, Professor
  • Laboratory: Natural Language Processing Laboratory
  • GPA Overall: 4.0/ Major: 4.0
• B.S. in Computer Science, National Tsing Hua University, HsinChu, Taiwan
  • July 2001 ~ June 2005
  • GPA Overall: 3.4/ Major: 3.5

Experience

• Research Scientist of Rakuten Institute of Technology(RIT) Boston (Sep. 2018 ~ Current)
• Part-time Research Scientist of CLEAR Lab, Department of Computer Science, University of Colorado Boulder, (Feb 2018 ~ Sep. 2018)
  • Participate in the Active Interpretation of Disparate Alternatives (AIDA) Project
  • Aimed to discover the relation between common semantic representations of knowledge elements and abstract meaning representation (AMR) for information synthesis.
  • Decoded common semantic representation of images to its corresponding AMRs, temporal, causal event relations and rich lexicon resources.
  • Integrated the AMRs to the Knowledge tuples in the ontology engine.
• Research Assistant of CLEAR Lab, Department of Computer Science, University of Colorado Boulder, (Jun. 2011 ~ Dec. 2017)
  • Participate in the Strategic Health IT Advanced Research Project for Normalization (SHARPn), focus on the NLP applications, including temporal and coreference analysis, that influence and extend uses of clinical data.
  • Participate in the Statistical Translation And GEneration using Semantics (STAGE) project, a collaboration of 5 Universities for Chinese-English statistical machine translation with semantics. We provide semantic role corpus as training and fusion data. An English light verb construction identification is also developed.
• Teaching Assistant of the course Operating Systems, Department of Computer Science, University of Colorado Boulder, USA, (Jan. 2011 ~ May. 2011)
  • Design and grade the programming assignment, including modifying Linux kernel, multi-threading programming, Minix kernel memory allocation, and Fuse file system.
  • Hold the Recitation 45 minutes a week and TA office hour twice a week.
• Research Assistant of Chinese Knowledge Information Processing Group, Institute of Information Science, Academia Sinica, Taiwan (Jun. 2009 ~ Aug. 2010)
  • Develop the Chinese lexical knowledge ontology and concept system.
  • Research the transformation from Chinese syntactic parse tree structures to Chinese concept structures.
• Engineer of Innovative DigiTech-Enabled Applications & Services Institute, Institute for Information Industry, Taiwan (Feb. 2009 ~ Jun. 2009)
  • Join the E-Dolls Project. Design the system hierarchy and implement both server and clinet side software.
  • Attain the Human Emotion-Judgement Project, which is related to the research of relation between human text and emotion
• Information System Instructor of Computer Office in National Security Bureau, National Army (Nov. 2007 ~ Jun. 2008)
  • Building, maintaining, and operating an internal E-learning system.
  • Constructing an internal machine translation system.
• Teaching Assisiant of the course Natural Language Processing Lab., ISA, NTHU (Sep. 2006 ~ Jan. 2007)
  • A graduate course delivered in English. Students are required to complete the assignment on class.
  • Responsible to revice students' codes, design the practice data, and maintain course website.

Publication

• Wei-Te Chen, and Martha Palmer. 2017. ``Unsupervised AMR-Dependency Parse Alignment'', In Proceedings of the European Chapter of the Association of Computational Linguistics (EACL) 2017, Valencia, Spain. PDF Bib Slides
• Wei-Te Chen. 2015. ``Learning to Map Dependency Parses to Abstract Meaning Representations'', In Proceedings of the ACL 2015 Student Research Workshop, Beijing, China. PDF Bib
• Wei-Te Chen, Claire Bonial, Martha Palmer. 2015. ``English Light Verb Construction Identification Using Lexical Knowledge'', In Proceedings of the AAAI-15, Austin, TX, USA. PDF Bib
• Wei-Te Chen, Will Styler. 2013. ``Anafora: A Web-based General Purpose Annotation Tool'', In Proceedings of the NAACL-HLT, Companion Volume: Demonstrations, Atlanta, GA, USA, pp. 433-438. PDF Bib
• Wei-Te Chen, Su-Chu Lin, Shu-Ling Huang, You-Shan Chung, and Keh-Jiann Chen. 2010. ``E-HowNet and Automatic Construction of a Lexical Ontology'', in Proceedings of International Conference on Computational Linguistics (COLING), pp. 45-48. PDF Bib
• Wen-Nan Wang, James Lee, Wei-Te Chen, Tzu-Chen Tsai, Eden Hsu. ``System and Method for Simulating Expression of Message'', U.S. Patent 8,285,552 PDF
• Chung-Chi Huang, Wei-Te Chen, and Jason S. Chang. 2009. ``Source Sentence Reordering for Phrase-based Machine Translation Systems'', in Proceedings of International Conference on Innovative Computing, Information and Control (ICICIC), pp. 95-98. PDF
• Chung-Chi Huang, Wei-Te Chen, and Jason S. Chang. 2009. ``Lexicalized Syntactic Reordering Framework for Word Alignment and Machine Translation'', in Proceedings of International Conference on the Computer Processing of Oriental Languages (ICCPOL), pp. 103-111. PDF
• Chung-Chi Huang, Wei-Te Chen, and Jason S. Chang. 2008. ``Bilingual Segmenter for Statistical Machine Translation'', in Proceedings of International Symposium on Universal Communication (ISUC), pp. 97-104.
• Chung-Chi Huang, Wei-Te Chen, and Jason S. Chang. 2008. ``Bilingual Segmentation for Alignment and Translation'', in Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), pp. 445-453. PDF
• Chung-Chi Huang, Wei-Te Chen, and Jason S. Chang. 2007. ``Improving Word Alignment Based on Extended Inversion Transduction Grammar'', in Proceedings of Recent Advances in Natural Language Processing (RANLP) PDF
• Wei-Teh Chen, 2007. ``Learning Syntactical Recording of Source Sentences for Statistical Machine Translation''. M.S. Graduate Thesis, National Tsing Hua University PDF

Demonstration System

• Anafora -- https://verbs.colorado.edu/anaforademo; GitHub
  • A web-based text annotation tool which facilities the creation of annotating corpora, including entity and relation, for variety NLP tasks.
  • Design the schema and data files in XML format, which makes the maintenance simple and organization representated.
  • Designed to be a lightweight, flexible annotation solution.
  • Development under Django and JavaScript.
• TermMine -- http://termmine.cs.nthu.edu.tw/TermMineSpace/
  • Mining Proper Noun on the World Wide Web.
  • Providing the accurate translation from back-end database.
  • Users rich the information, such as better translations and tags.
  • Cooperate with Galaxy Software Services Corporation
  • Development under PHP(with framework CakePHP)/JavaScript/MySQL

Computer Skills

• Language
  • Python, C/C++, Java
• Cluster Computing Framework
  • Apache Spark, Apache Hadoop
• Deep Learning Library
  • PyTorch, Keras
• Web Development
  • jQuery, CSS, JavaScript
• Web Framework
  • Django, codeIgniter, CakePHP

Honor

• 2016 Summer Graduate School Fellowship, Graduate School, University of Colorado Boulder
• Research Community Development Awards Fall 2011, Department of Computer Science, University of Colorado Boulder. (2011)
  • Travel Grant to attend ACL 2012 in Jeju, Korea
  • Amount: $1,750
• Dean's Outstanding Merit Fellowship, College of Engineering and Applied Science, University of Colorado Boulder. (2010~2011)
• Member of The Phi-Tau-Phi Scholastic Honor Society (Top 2% Students), Jun. 2006

Actitives

• Vice Leader of Softball Team, CS, NTHU (Jun. 2003 ~ Jun. 2004)
• Engineer Chief, Tsing Hua Broadcast Station, NTHU (Mar. 2003 ~ Mar. 2004)
• Chairman of Computer Science Summer Camp in 2003, CS, NTHU
• Member of Computer Science Student Association, CS, NTHU (Mar. 2002 ~ Mar. 2003)