The growing importance of multilingual information retrieval and machine translation has made multilingual ontologies an extremely valuable resource. Since the construction of an ontology from scratch
A Knowledge-Based Approach for Unsupervised Chinese Coreference Resolution (2008)
Coreference resolution is the process of determining the entity that noun phrases refer to. A great deal of research has been done on this task in English, using approaches ranging from those based...
Raising the Bar: Stacked Conservative Error Correction Beyond Boosting (2008)
Dekai Wu, Grace Ngai, Marine Carpuat
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...
Radu Florian, John C. Henderson, Grace Ngai
Transformation-based learning has been successfully employed to solve many natural language processing problems. It has many positive features, but one drawback is that it does not provide estimates...
Flow control considerations in network-based architectures Ph.D. Project report by G.Ngai (2007)
Magda Konstantinidou, S. Konstantinidou, Grace Ngai
In network-based parallel architectures, the issues of fairness, freedom of deadlock due to finite buffers and guaranteed message delivery can affect not only performance but even more importantly,...
David Yarowsky, Grace Ngai, Richard Wicentowski
This paper describes a system and set of algorithms for automatically inducing stand-alone monolingual part-of-speech taggers, base noun-phrase bracketers, named-entity taggers and morphological...
Grace Ngai, Marine Carpuat, Pascale Fung
This paper presents a first step towards the creation of a bilingual ontology through the alignment of two monolingual ontologies: the American English WordNet and the Mandarin Chinese HowNet. These...
Extractive Summarization (2007)
We propose Hidden Markov models with unsupervised training for extractive summarization. Extractive summarization selects salient sentences from documents to be included in a summary. Unsupervised...
Inducing Multilingual Text Analysis Tools via Robust Projection across Aligned Corpora (2007)
Yarowsky, David, Ngai, Grace, Wicentowski, Richard
This paper describe system and set of automatically inducing stand-alone monolingual part-of-speech taggers, base noun-phrase bracketers, named-entity taggers and morphological analyzers for an...
Joining forces to resolve lexical ambiguity: East meets West in Barcelona (2004)
Richard Wicentowski, Grace Ngai, Dekai Wu
This paper describes the component models and combination model built as a joint effort between Swarthmore College, Hong Kong PolyU, and HKUST. Though other models described elsewhere contributed to...
Semantic Role Labeling with Boosting, SVMs, Maximum Entropy, SNOW, and Decision Lists (2004)
Grace Ngai, Dekai Wu, Marine Carpuat, Chi-shing Wang, Chi-yung Wang
This paper describes the HKPolyU-HKUST systems which were entered into the Semantic Role Labeling task in Senseval-3. Results show that these systems, which are based upon common machine learning...
N-fold Templated Piped Correction (2004)
Dekai Wu Grace, Grace Ngai, Marine Carpuat
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...
Joining forces to resolve lexical ambiguity: East meets West in Barcelona (2004)
Richard Wicentowski, Grace Ngai, Dekai Wu
This paper describes the component models and combination model built as a joint effort between Swarthmore College, Hong Kong PolyU, and HKUST. Though other models described elsewhere contributed to...
Why nitpicking works: Evidence for Occam’s razor in error correctors (2004)
Dekai Wu, Grace Ngai, Marine Carpuat
Empirical experience and observations have shown us when powerful and highly tunable classifiers such as maximum entropy classifiers, boosting and SVMs are applied to language processing tasks, it is...
A stacked, voted, stacked model for named entity recognition (2003)
Dekai Wu, Grace Ngai, Marine Carpuat
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,...
A Stacked, Voted, Stacked Model for Named Entity Recognition (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,...
A Stacked, Voted, Stacked Model for Named Entity Recognition (2003)
Dekai Wu And, Dekai Wu, Grace Ngai, Marine Carpuat
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,...
A Stacked, Voted, Stacked Model for Named Entity Recognition (2003)
Dekai Wu, Grace Ngai, Marine Carpuat
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,...
Boosting for Named Entity Recognition (2002)
Dekai Wu, Grace Ngai, Marine Carpua, Jeppe Larsen, Yongsheng Yang, Clear Water Bay
This paper presents a system that applies boosting to the task of named-entity identi cation. The CoNLL-2002 shared task, for which the system is designed, is language-independent named-entity...
Transformation-Based Learning in the Fast Lane (2001)
Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and...
Multidimensional Transformation-Based Learning (2001)
This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks...
Man [and Woman] vs. Machine: A Case Study in Base Noun Phrase Learning (2001)
A great deal of work has been done demonstrating the ability of machine learning algorithms to automatically extract linguistic knowledge from annotated corpora. Very little work has gone into...
Rule Writing or Annotation: Cost-efficient Resource Usage for Base Noun Phrase Chunking (2001)
This paper presents a comprehensive empirical comparison between two approaches for developing a base noun phrase chunker: human rule writing and active learning using interactive real-time human...
Florian, Radu, Henderson, John C., Ngai, Grace
Transformation-based learning has been successfully employed to solve many natural language processing problems. It has many positive features, but one drawback is that it does not provide estimates...
Multidimensional transformation-based learning (2001)
This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm (Brill, 1995) to be applied to multiple classication tasks by training...
Transformation-based learning in the fast lane (2001)
Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and...
Radu Florian, John C. Henderson, Grace Ngai
Transformation-based learning has been success-fully employed to solve many natural language processing problems. It has many positive fea-tures, but one drawback is that it does not provide...
Rule writing or annotation: Cost-efficient resource usage for base noun phrase chunking (2000)
Email:{gyn, yarowsky}cs. jhu. edu This paper presents a comprehensive empirical comparison between two approaches for developing a base noun phrase chunker: human rule writing and active learning...
Rule Writing or Annotation: Cost-efficient Resource Usage for Base Noun Phrase Chunking (2000)
This paper presents a comprehensive empirical comparison between two approaches for developing a base noun phrase chunker: human rule writing and active learning using interactive realtime human...
Automatic Grammar Induction: Combining, Reducing and Doing Nothing (2000)
Eric Brill, John C. Henderson, Grace Ngai
This paper surveys three research directions in parsing. First, we look at methods for both automatically generating a set of diverse parsers and combining the outputs of dierent parsers into a...
Man vs. Machine: A Case Study in Base Noun Phrase Learning (1999)
A great deal of work has been done demonstrating the ability of machine learning algorithms to automatically extract linguistic knowledge from annotated corpora. Very little work has gone into...
Dynamic User Model Construction with Bayesian Networks for Intelligent Information Queries (1999)
Eugene Santos, Scott M. Brown, Moises Lejter, Grace Ngai, Sheila B. Banks, ...
The complexity of current software applications is overwhelming users. The need exists for intelligent interface agents to address the problems of increasing taskload that is overwhelming the human...
A Comparison of Memory Models for Multiprocessor Systems (1997)
Multiprocessor systems have become common in recent years, due to the increasing computing demand of applications, and the decrease of processor prices. By combining the power of several processors,...