Aida Nematzadeh
Background
I am a second year PhD student in the Computational Linguistics group in the Department of Computer Science at the University of Toronto. My supervisor is Suzanne Stevenson.
I got my Bachelor's degree in Computer Engineering from Amirkabir University of Technology. My Bachelor's project was "Semantic Tagging of Persian Text".
Education
- PhD in Computer Science, University of Toronto, Jan. 2010 - present
- MSc in Computer Science, University of Toronto, Sep. 2008 - Jan. 2010
- BSc in Computer Engineering, Amirkabir University of Technology, Sep. 2003 - Sep. 2007
Publications
-
Child Acquisition of Multiword Verbs: A Computational Investigation
A. Nematzadeh, A. Fazly, and S. Stevenson
In T. Poibeau, A. Villavicencio, A. Korhonen and A. Alishahi (eds). Cognitive Aspects of Computational Language Acquisition, Springer (in preparation) - A Computational Study of Late Talking in Word-Meaning Acquisition
A. Nematzadeh, A. Fazly, and S. Stevenson
Proceedings of the 33rd Annual Conference of the Cognitive Science Society, Boston, Massachusetts, July 2011 [poster] [bibtex] - The Role of Statistical Evidence in Child Acquisition of Multiword Verbs
A. Nematzadeh
Master's paper. Department of Computer Science, University of Toronto. January 2010 [bibtex] - Acquiring Multiword Verbs: The Role of Statistical Evidence
A. Fazly, A. Nematzadeh, and S. Stevenson
Proceedings of the 31st Annual Conference of the Cognitive Science Society, Amsterdam, The Netherland, July 2009 [bibtex]
Research Interests
- Computational Models of Language Acquisition
- Lexical Semantics
Research Projects
Child Acquisition of Multiword Expressions
[with Afsaneh
Fazly and Suzanne Stevenson]
Multiword expressions convey a single meaning while allowing syntactic
variations. Their meanings range from entirely literal to non-literal
(e.g., "give a shout" versus "give me an apple"). These expressions are
very frequent in many languages and children successfully learn them in
addition to the lexicon and grammar of their language. An important
question is how children identify non-literal multiword expressions. We
argue that statistical regularities of non-literal expressions are useful
in separating them from literal ones. We devise different statistical
measures drawn on properties of non-literal expressions. By evaluating
these measures on the CHILDES database, we show that these regularities
are available in and easily extractable from child-directed speech.
Courses
- CSC2541 Topics in Machine Learning: Bayesian Methods for Machine Learning, Winter 2011
- CSC2515 Introduction to Machine Learning, Fall 2010
- CSC2599 Reading Course in Modelling Early Word Learning in Children, Winter 2009
- CSC2511 Natural Language Computing, Winter 2009
- CSC2501 Introduction to Computational Linguistics, Fall 2008
- CSC2431 Topics in Computational Molecular Biology, Fall 2008
Recent Teaching Assistantships
- CSC148 Introduction to Computer Science, Winter 2011
- CSC108 Introduction to Computer Programming, Winter 2011
- CSC180 Introduction to Programming, Fall 2010, Fall 2009, Fall 2008
- CSC104 The Why and How of Computing, Winter 2010, Winter 2009