Jackie Chi Kit Cheung
Ph.D., Computational Linguistics group
Department of Computer Science
University of Toronto
10 King's College Rd., Room 3302
Toronto, Ontario M5S 3G4
Office: Pratt 283E
Phone: 1 (416) 946-4005
E-mail: jcheung with the usual suffix (@cs.toronto.edu)
The goal of my research is to understand the meaning in text and speech (semantic analysis), in order to automatically generate language that is fluent and appropriate to the context. This involves observing statistical patterns of language use, and then developing algorithms that can automatically reason with these statistically derived meaning representations (distributional semantics). The reasoning and inference component can then be used in language generation applications, such as in automatic summarization.
Topics in computational linguistics that I have published on include computational semantics, parsing and discourse analysis, and automatic summarization.
I was supported by a Facebook Fellowship for 2013–2014.
News: I am starting as an Assistant Professor in the School of Computer Science at McGill University in January, 2015! I will be looking for motivated and qualified students who are interested in undertaking research in computational linguistics.
Academic History
2010–2014 | Ph.D. in Computer Science at the University of Toronto | Advisor: Gerald Penn |
2008–2010 | M.Sc. in Computer Science at the University of Toronto | Advisor: Gerald Penn |
2004–2008 | B.Sc. (Honours) in Computer Science, minors in Linguistics and German at the University of British Columbia | Advisor: Giuseppe Carenini |
Spring 2012 | Internship in the NLP group, Microsoft Research | Mentors: Lucy Vanderwende and Hoifung Poon |
Summer 2011 | Internship in the Speech Group, Microsoft Research | Mentor: Xiao Li |
CV
Publications and Data
Refereed Publications
- Jackie C.K. Cheung and Gerald Penn. 2014. Unsupervised Sentence Enhancement for Automatic Summarization EMNLP.
- Jackie C.K. Cheung and Gerald Penn. 2013. Probabilistic Domain Modelling With Contextualized Distributional Semantic Vectors ACL.
Data: Hyperparameter settings - Jackie C.K. Cheung and Gerald Penn. 2013. Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain. ACL.
- Jackie C.K. Cheung, Hoifung Poon and Lucy Vanderwende. 2013. Probabilistic Frame Induction. NAACL.
- Giuseppe Carenini, Jackie C.K. Cheung and Adam Pauls. 2012. Multi-Document Summarization of Evaluative Text. Computational Intelligence.
- Jackie C.K. Cheung and Gerald Penn. 2012. Evaluating Distributional Models of Semantics for Syntactically Invariant Inference. EACL.
Data: Evaluation code and preprocessed evaluation data - Jackie C.K. Cheung and Gerald Penn. 2012. Unsupervised Detection of Downward-Entailing Operators By Maximizing Classification Certainty. EACL.
Data: Expanded list of downward-entailing operator candidates - Jackie C.K. Cheung and Xiao Li. 2012. Sequence Clustering and Labeling for Unsupervised Query Intent Discovery. WSDM.
- Jackie C.K. Cheung and Gerald Penn. 2010. Utilizing Extra-sentential Context for Parsing.
EMNLP.
Data: Raw between-sentence parallelism statistics - Jackie C.K. Cheung and Gerald Penn. 2010. Entity-Based Local Coherence Modelling Using Topological Fields. ACL.
- Jackie C.K. Cheung and Gerald Penn. 2009. Topological Field Parsing of German. ACL-IJCNLP.
Data: Parsing models - Jackie C.K. Cheung, Giuseppe Carenini and Raymond T. Ng. 2009. Optimization-Based Content Selection for Opinion Summarization. UCNLG+Sum.
- Giuseppe Carenini and Jackie C.K. Cheung. 2008. Extractive vs. NLG-based Abstractive Summarization of Evaluative Text: The Effect of Corpus Controversiality. INLG.
Theses
- Jackie C.K. Cheung. 2014. Distributional Semantics for Robust Automatic Summarization Ph.D. dissertation.
- Jackie C.K. Cheung. 2010. Parsing German Topological Fields with Probabilistic Context-Free Grammars. M.Sc. paper.
- Jackie C.K. Cheung. 2008. Comparing Abstractive and Extractive Summarization of Evaluative Text: Controversiality and Content Selection. Honours thesis.