Vincent Ng

Assistant Professor of Computer Science Human Language Technology Research Institute University of Texas at Dallas B.S. in Computer Science, Carnegie Mellon University Ph.D. in Computer Science, Cornell University Contact Information Office hours for Summer 2010: By appointment only Office: ECSS 3.404 Phone: 972-883-4581 (office), 972-883-2349 (fax) Email: vince at hlt dot utdallas dot edu Postal address: Computer Science Department The University of Texas at Dallas 2601 N. Floyd Rd. MS EC31 Richardson, TX 75083-0688

From left to right: Altafur, me, Sajib, Saidul (May 2009)

---

Research Interests

My general research area is machine learning of natural language. My recent projects have focused primarily on developing unsupervised and semi-supervised machine learning techniques for natural language processing, with the goal of reducing the amount of annotated data needed to build NLP applications and process resource-scarce languages. Areas in which my students and I have been working include:

• text mining, clustering, and classification
• discourse
• information extraction
• morphology and part-of-speech tagging

Research

• Recent papers
  • Topic-wise, Sentiment-wise, or Otherwise? Identifying the Hidden Dimension for Unsupervised Text Classification.
    Sajib Dasgupta and Vincent Ng.
    Proceedings of EMNLP, 2009.

  • Supervised Models for Coreference Resolution.
    Altaf Rahman and Vincent Ng.
    Proceedings of EMNLP, 2009.

  • Mine the Easy, Classify the Hard: A Semi-Supervised Approach to Automatic Sentiment Classification.
    Sajib Dasgupta and Vincent Ng.
    ACL-IJCNLP 2009: Proceedings of the Main Conference, 2009.

  • Semi-Supervised Cause Identification from Aviation Safety Reports.
    Isaac Persing and Vincent Ng.
    ACL-IJCNLP 2009: Proceedings of the Main Conference, 2009.

  • Graph-Cut-Based Anaphoricity Determination for Coreference Resolution.
    Vincent Ng.
    NAACL HLT 2009: Proceedings of the Main Conference, 2009.

  • Weakly Supervised Part-of-Speech Tagging for Morphologically-Rich, Resource-Scarce Languages.
    Kazi Saidul Hasan and Vincent Ng.
    Proceedings of EACL, 2009.

  • Learning-Based Named Entity Recognition for Morphologically-Rich, Resource-Scarce Languages.
    Kazi Saidul Hasan, Altaf Rahman, and Vincent Ng.
    Proceedings of EACL, 2009.

• (Almost) complete list of papers (in reverse chronological order, grouped by topic)
• Data
• Talk slides

Professional Activities

• Local organizer, North American Computational Linguistics Olympiad (NACLO 2009, NACLO 2010), Dallas site
• Recent program committees and conference review panels
  • EMNLP 2009, ACL-IJCNLP 2009, NAACL HLT 2009, IJCAI 2009, CoNLL 2009, SIGDIAL 2009, SSLNLP 2009, DAARC 2009, PACLIC 2009, WikiAI 2009, AND 2009
• Journal referee (recent)
  • Computational Linguistics (2009, 3 articles), Journal of AI Research (2009), ACM Computing Surveys (2009, 2 articles), Data and Knowledge Engineering (2009, 2 articles)
• Panelist, Student Research Workshops at EACL 2009 and NAACL HLT 2009
• Review panel, National Science Foundation (2008, 2009)
• Ad-hoc proposal reviewer, National Science Foundation (2009)
• Ad-hoc proposal reviewer, Qatar National Research Fund (2009)
• More ...

Teaching

• CS 4365: Artificial Intelligence (Spring 2006, Spring 2007, Spring 2008, Spring 2009, Spring 2010)
• CS 4375: Introduction to Machine Learning (Fall 2006, Fall 2007, Fall 2008, Fall 2009)
• CS 6364: Artificial Intelligence (Spring 2009)
• CS 6375: Machine Learning (Fall 2005, Fall 2006, Fall 2007, Fall 2010)
• CS 2305: Discrete Math for Computing I (Fall 2004)

Miscellaneous

I am the professor of artificial intelligence for the undergrads.

---

Last modified: Wed May 5 23:17:56 2010