Publication List

Journals

Conferences

  • Michael X. Huang, Will W.W. Tang, Kenneth W.K. Lo, C.K Lau, Grace NGAI and Stephen C.F. Chan. "MelodicBrush: A Cross-Modal Link between Ancient and Digital Art Forms". In CHI 2012 Interactivity-Exploration Austin, Texas, May 2012

  • Michael X. Huang, Will W.W. Tang, Kenneth W.K. Lo, C.K Lau, Grace NGAI and Stephen C.F. Chan. "MelodicBrush: A Novel System for Cross-Modal Digital Art Creation Linking Calligraphy and Music". In ACM Conference on Designing Interactive Systems (DIS '12) Newcastle, June 11-15, 2012

  • Kenneth W.K. Lo, Will W.W. Tang, Hong Va Leong, Alvin T.S. Chan, Stephen C.F. Chan and Grace NGAI. "'i*Chameleon: A Unified Web Service Framework for Integrating Multi-Modal Interaction Devices". In 9th IEEE Workshop on Managing Ubiquitous Communications and Services (MUCS '12) Lugano, March 2012

  • Will W.W. Tang, Kenneth W.K. Lo, Grace NGAI, Stephen C.F. Chan, Alvin T.S. Chan and Hong-va Leong. "i*Chameleon: A Scalable and Extensible Framework for Multimodal Interaction". In CHI '11 Extended Abstracts on Human Factors in Computing Systems (CHI 2011) Vancouver, Canada: May 2011

  • Grace NGAI, Stephen C.F. Chan, Vincent T.Y. Ng, Joey C.Y. Cheung, Sam S.S. Choy, Winnie W.Y. Lau and Jason T.P. Tse. "i*CATch: A Scalable, Plug-n-Play Wearable Computing Framework for Novices and Children". Proceedings of the Twenty-Seventh Annual SIGCHI Conference on Human Factors in Computing Systems (CHI 2010) Atlanta, GE: April 2010. Best CHI Papers Honorable Mention Award.

  • Grace NGAI, Stephen C.F. Chan, Winnie W.Y. Lau and Joey C.Y. Cheung. "The TeeBoard: an Education-Friendly Construction Platform for E-Textiles and Wearable Computing" Proceedings of the Twenty-Sixth Annual SIGCHI Conference on Human Factors in Computing Systems (CHI 2009) Boston, USA: April 2009

    The field of wearable computing and e-textiles has recently attracted much interest from the research and general community. Recent developments in this field raises the possibility of e-textile construction kits for hobbyists and novices alike. The unique nature of wearable computing and e-textiles also gives it a lot of potential as an educational computing topic, as it allows students to exercise their creativity and imagination while learning about computing and technology. However, there are numerous difficulties involved in deploying existing technology in an educational environment. Current state of the art technology and techniques are not yet robust or reliable enough to stand up to the demands of educational computing, and they require a high level of skill from the user. In this paper, we present the TeeBoard, a constructive platform for e-textiles and wearable computing that is designed specifically to lower the floor for the integration of e-textiles into educational computing.

  • Grace NGAI, Stephen C.F. Chan, Winnie W.Y. Lau and Joey C.Y. Cheung. "An Education-Friendly Construction Platform for Wearable Computing" In CHI '09 Extended Abstracts on Human Factors in Computing Systems (CHI 2009) Boston, USA: April 2009

    Wearable computing and e-textiles has a lot of potential as an educational computing topic. They allow students to exercise their creativity and imagination while learning about concepts in computing and technology. However, there are still numerous difficulties involved in deploying existing technology in an educational environment. In this paper, we present the TeeBoard, a construction platform for e-textiles and wearable computing that is designed to be robust, reliable, easy to construct and to program. It has also passed initial tests in a practical workshop for high school students.

  • Winnie W.Y. Lau, Grace NGAI, Stephen C.F. Chan, and Joey C.Y. Cheung. "Learning programming through fashion and design: a pilot summer course in wearable computing for middle school students". Proceedings of the 40th ACM technical symposium on Computer Science Education (SIGCSE 2009). Chattanooga, USA: Mar 2009, pp 504-508.

    As enrollments in engineering and computer science programs around the world have fallen in recent years, those who wish to see this trend reversed take heart from findings that children are more likely to develop an abiding interest in technology if they are exposed to it at an early age [3, 9]. In line with this research, we now see more summer camps and workshops being offered to middle school students with the objective of teaching programming and computer technology [1, 6, 8, 12]. To offer students a stimulating and interesting environment while teaching computing subjects, the learning tools in these camps usually revolve around robots and graphical programming of animations or games. These tools tend to mainly attract youngsters who like robotics or game design. However, we believe that we can improve the diversity of the student pool by introducing other topics. In this paper, we describe our experience in designing and organizing a programming course that focuses on wearable computing, fashion and design for middle school students. We will show that 1) wearable computing is interesting and inspiring to the students, 2) wearable computing motivates both boys and girls to learn technology and computing, which implies that it may be able to increase the potential computer science population, 3) wearable computing can provide a space for students to exercise their creativity while at the same time, teaching them about technology and programming.

  • Joey C.Y. Cheung, Grace NGAI, Stephen C.F. Chan, and Winnie W.Y. Lau. "Filling the Gap in Programming Instruction: A Text-enhanced Graphical Programming Environment for Junior High Students". Proceedings of the 40th ACM technical symposium on Computer Science Education (SIGCSE 2009). Chattanooga, USA: Mar 2009, pp 276-280.

    To address the unique demands and challenges of educational computing, various kinds of environments, including graphics-rich and textual environments, have been proposed for use in introductory courses to provide students with a rich and interesting learning environment. In our experience, students in Grade 7 and younger respond best to the graphics environments while senior high school students prefer a conventional textual programming environment. Clearly, this leaves a gap at Grade 11-13, with students often on the one hand finding the graphics-based environments too limited and on the other finding the textual environments too difficult. In this paper, we propose a text-enhanced graphical programming environment which is innovative and interactive, and designed for junior high students with no programming experience. This environment allows students to design their own creative stories or programs. They build their programs using drag-and-drop iconic blocks, but unlike other, similar icon-based programming languages, they are also presented with the syntax of the actual program they are constructing in real-time. Once a particular icon block has been dropped in the programming area, the syntax statements corresponding to that block is immediately generated and presented to the user. The environment also allows them to modify the code without any limitations. Our results show that our textual-graphical hybrid environment has a positive impact on the learning experience of the students.

  • Grace NGAI, Stephen C.F. Chan, Winnie W.Y. Lau and Joey C.Y. Cheung. A Framework for Collaborative eTextiles Design -- An Introduction to Co-eTex. 13th International Conference on CSCW in Design. Santiago, Chile: April 2009

  • Jason T.P Tse, Stephen C.F. Chan, Grace NGAI, Joey C.Y. Cheung and Vincent T.Y. Ng. DYNAMIC COLLABORATIVE ROBOTIC PLATFORM -- A BRIEF INTRODUCTION. 13th International Conference on CSCW in Design. Santiago, Chile: April 2009

  • Grace NGAI and Chi-Shing WANG. "A Clustering Approach for Unsupervised Chinese Coreference Resolution". 5th SIGHAN Workshop on Chinese Language Processing. COLING/ACL Workshop. Sydney: July 2006, pp 40-47

  • Grace Ngai, Stephen C.F. Chan and Vincent T.Y. Ng. "Becoming fluent in Java (or any computer language): Overlearning and Active Learning in Introductory Computer Science Learning". Asia-Pacific Education Research Association Conference 2006. Hong Kong: November 2006

  • Stephen C.F. Chan, Vincent T.Y. Ng, Grace Ngai. "A Framework for Service Learning in Professional Disciplines". Asia-Pacific Education Research Association Conference 2006. Hong Kong: November 2006

  • Stephen C.F. Chan, Vincent T.Y. Ng, Grace NGAI and Cane W.K. Leung. "Service Learning -- Information Technology Education through Community Service". IADIS International Conference e-Society 2006. Dublin: July 2006

  • Dekai WU, Grace NGAI, and Marine CARPUAT. "Why Nitpicking Works: Evidence for Occam's Razor in Error Correctors". 20th International Conference on Computational Linguistics (COLING-2004). Geneva: Aug 2004, pp 404-410

  • Grace NGAI, Dekai WU, Marine CARPUAT, Chi-Shing WANG, and Chi-Yung WANG. "Semantic Role Labeling with Boosting, SVMs, Maximum Entropy, SNOW, and Decision Lists". Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text (Senseval-3). ACL-2004 Workshop. Barcelona: Jul 2004, pp 186-186

  • Richard WICENTOWSKI, Grace NGAI, Dekai WU, Marine CARPUAT, Emily THOMFORDE, and Adrian PACKEL. "Joining forces to resolve lexical ambiguity: East meets West in Barcelona". Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text (Senseval-3). ACL-2004 Workshop. Barcelona: Jul 2004, pp 262-264

  • Dekai WU, Grace NGAI, and Marine CARPUAT. "Raising the Bar: Stacked Conservative Error Correction Beyond Boosting". Fourth International Conference on Language Resources and Evaluation (LREC-2004). Lisbon: May 2004, pp 21-24.

    We introduce a conservative error correcting model, Stacked TBL, that is designed to improve the performance of even high-performing models like boosting, with little risk of accidentally degrading performance. Stacked TBL is particularly well suited for corpus-based natural language applications involving high-dimensional feature spaces, since it leverages the characteristics of the TBL paradigm that we appropriate. We consider here the task of automatically annonating named entities in text corpora. The task does pose a number of challenges for TBL, to which there are some simple yet effective solutions. We discuss the empirical behavior of Stacked TBL, and consider evidence that despite its simplicity, more complex and time-consuming variants are not generally required.

  • Dekai WU, Grace NGAI, and Marine CARPUAT. "N-fold Templated Piped Correction". First International Joint Conference on Natural Language Processing (IJCNLP-2004). Hainan, China: Mar 2004, pp 632-637.

    We describe a broadly-applicable conservative error correcting model, N-fold Templated Piped Correction (NTPC), that consistently improves the accuracy of existing high-accuracy base models. Under circumstances where most obvious approaches actually reduce accuracy more than they improve it, NTPC nevertheless comes with little risk of accidentally degrading performance. NTPC is particularly well suited for natural language applications involving high-dimensional feature spaces, such as bracketing and disambiguation tasks, since its easily customizable template-driven learner allows efficient search over the kind of complex feature combinations that have typically eluded the base models. We show empirically that NTPC yields small but consistent accuracy gains on top of even high-performing models like boosting. We also give evidence that the various extreme design parameters in NTPC are indeed necessary for the intended operating range, even though they diverge from usual practice.

  • Pascale FUNG, Grace NGAI and Chi-Shun CHEUNG, "Combining Optimal Clustering and Hidden Markov Models for Extractive Summarization", Workshop on Multilingual Summarization and Question Answering, ACL-2003 Workshop. Sapporo, July 2003

  • Dekai WU, Grace NGAI, and Marine CARPUAT. "A stacked, voted, stacked model for named entity recognition". Computational Natural Language Learning (CoNLL-2003), at Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL-2003). Edmonton, Canada: May 2003.

    This paper investigates stacking and voting methods for combining strong classifiers like boosting, SVM, and TBL, on the named-entity recognition task. We demonstrate several effective approaches, culminating in a model that achieves error rate reductions on the development and test sets of 63.6% and 55.0% (English) and 47.0% and 51.7% (German) over the CoNLL-2003 standard baseline respectively, and 19.7% over a strong AdaBoost baseline model from CoNLL-2002.

  • Grace NGAI, Marine CARPUAT and Pascale FUNG, "Identifying Concepts Across Languages: A First Step towards a Corpus-based Approach to Automatic Ontology Alignment". In Proceedings of COLING-02, Taipei, Taiwan: 24th Aug-1st Sept, 2002, pp 737-743

  • Dekai WU, Grace NGAI, Marine CARPUAT, Jeppe LARSEN, and Yongshen YANG. "Boosting for named entity recognition". Computational Natural Language Learning (CoNLL-2002), at 19th International Conference on Computational Linguistics (Coling-2002), 195-198. Taipei: Sep 2002.

    This paper presents a system that applies boosting to the task of named-entity identification. The CoNLL-2002 shared task, for which the system is designed, is language-independent named-entity recognition. Using a set of features which are easily obtainable for almost any language, the presented system uses boosting to combine a set of weak classifiers into a final system that performs significantly better than that of an off-the-shelf maximum entropy classifier.

  • Marine CARPUAT, Grace NGAI, Pascale FUNG and Kenneth CHURCH, "Creating a Bilingual Ontology: A Corpus-Based Approach for Aligning WordNet and HowNet". In Proceedings of the 1st Global WordNet Conference, Mysore, January 2002.

  • Grace NGAI and Radu FLORIAN, "Transformation-Based Learning in the Fast Lane", In Proceedings of the Second Conference of the North American Chapter of the Association for Computational Linguistics, (ISBN: 1-55860-788-9), pp. 40--47, 2001.

  • David YAROWSKY and Grace NGAI, ``Inducing Multilingual POS Taggers and NP Bracketers via Robust Projection across Aligned Corpora'', In Proceedings of the Second Conference of the North American Chapter of the Association for Computational Linguistics (ISBN: 1-55860-788-9), pp. 200--207, 2001.

  • David YAROWSKY, Grace NGAI and Richard WICENTOWSKI. ``Inducing Multilingual Text Analysis Tools via Robust Projection across Aligned Corpora.'' In Proceedings of HLT 2001, First International Conference on Human Language Technology Research (ISBN: 1-55860-786-2), pp. 161--168, 2001

  • Radu FLORIAN and Grace NGAI, ``Multidimensional Transformation-Based Learning'', In Proceedings of the Fifth Conference on Natural Language Learning, pp. 1--6, Toulouse, July 2001.

  • Grace NGAI and D. Yarowsky, ``Rule Writing or Annotation: Cost-efficient Resource Usage for Base Noun Phrase Chunking'', In Proceedings of the 38th Meeting of the Association for Computational Linguistics (ISBN: 1-55860-731-5), pp. 117-125, 2000.

  • Radu FLORIAN, John HENDERSON and Grace NGAI, ``Coaxing Confidence from an Old Friend: Probabilistic Classifications from Transformation Rule Lists'', In EMNLP-2000, pp. 26--34, Hong Kong, 2000.

  • Eric BRILL, John HENDERSON and Grace NGAI, ``Automatic Grammar Induction: Combining, Reducing and Doing Nothing'', International Workshop on Parsing Technology, 2000.

  • Eric BRILL and Grace NGAI, ``Man [and Woman] vs. Machine: A Case Study in Base Noun Phrase Learning'', In Proceedings of the 37th Meeting of the Association for Computational Linguistics (ISBN: 1-55860-609-2), pp. 65--72, 1999.

  • E. Santos Jr., S. M. Brown, M. Lejter, G. NGAI, S.B. Banks and M.R. Stytz, ``Dynamic User Model Construction with Bayesian Networks for Intelligent Information Queries'', In Proceedings of the 11th International FLAIRS Conference, pp. 3--7, Orlando 1999.
    • Back to the home page.