H
Hwee Tou Ng
Researcher at National University of Singapore
Publications - 203
Citations - 14419
Hwee Tou Ng is an academic researcher from National University of Singapore. The author has contributed to research in topics: Machine translation & Sentence. The author has an hindex of 58, co-authored 184 publications receiving 12923 citations. Previous affiliations of Hwee Tou Ng include Agency for Science, Technology and Research & DSO National Laboratories.
Papers
More filters
Journal ArticleDOI
A machine learning approach to coreference resolution of noun phrases
TL;DR: The learning approach to coreference resolution of noun phrases in unrestricted text is presented, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches.
Proceedings ArticleDOI
Feature selection, perceptron learning, and a usability case study for text categorization
TL;DR: An automated learning approach to text categorization based on perception learning and a new feature selection metric, called correlation coefficient, is described and empirical results indicate that this approach outperforms the best published results on this % uters collection.
Proceedings ArticleDOI
The CoNLL-2014 Shared Task on Grammatical Error Correction
Hwee Tou Ng,Siew Mei Wu,Ted Briscoe,Christian Hadiwinoto,Raymond Hendy Susanto,Christopher Bryant +5 more
TL;DR: The CoNLL-2014 shared task was devoted to grammatical error correction of all error types as discussed by the authors, where a participating system is expected to detect and correct grammatical errors of all types.
Posted Content
Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach
Hwee Tou Ng,Hian Beng Lee +1 more
TL;DR: This approach integrates a diverse set of knowledge sources to disambiguate word sense, including part of speech of neighboring words, morphological form, the unordered set of surrounding words, local collocations, and verb-object syntactic relation.
Proceedings ArticleDOI
Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach
Hwee Tou Ng,Hian Beng Lee +1 more
TL;DR: This paper used an exemplar-based learning algorithm for word sense disambiguation, integrating a diverse set of knowledge sources, including part of speech of neighboring words, morphological form, the unordered set of surrounding words, local collocations, and verb-object syntactic relation.