Afsaneh Fazly
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Afsaneh Fazly has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Suzanne Stevenson
Department of Computer Science University of Toronto
5 shared publications - Ryan North
University of Toronto
2 shared publications Afra Alishahi
Department of Computational Linguistics, Saarland University
1 shared publication- Michael Jamieson
Department of Computer Science, University of Toronto, 10 King's College Road, Room 3302, Toronto, Ontario, Canada M5S3G4
1 shared publication Paul Cook
1 shared publicationSuzanne Stevenson
Department of Computer Science, University of Toronto
1 shared publication
Latest Publications
- 3 August 2010
- Published by Wiley in Cognitive Science
- Vol. 34 (6) , 1017-1063
A Probabilistic Computational Model of Cross‐Situational Word Learning
Words are the essence of communication: They are the building blocks of any language. Learning the meaning of words is thus one of the most important aspects of language acquisition: Children must first learn words before they can combine them into complex utterances. Many theories have been developed to explain the impressive efficiency of young children in acquiring the vocabulary of their language, as well as the developmental patterns observed in the course of lexical acquisition. A major source of disagreement among the different theories is whether children are equipped with special mechanisms and biases for word learning, or their general cognitive abilities are adequate for the task. We present a novel computational model of early word learning to shed light on the mechanisms that might be at work in this process. The model learns word meanings as probabilistic associations between words and semantic elements, using an incremental and probabilistic learning mechanism, and drawing only on general cognitive abilities. The results presented here demonstrate that much about word meanings can be learned from naturally occurring child‐directed utterances (paired with meaning representations), without using any special biases or constraints, and without any explicit developmental changes in the underlying learning mechanism. Furthermore, our model provides explanations for the occasionally contradictory child experimental data, and offers predictions for the behavior of young word learners in novel situations.
- 3 August 2010
- Published by Wiley in Cognitive Science
- Vol. 34 (6) , 1017-1063
A Probabilistic Computational Model of Cross‐Situational Word Learning
Words are the essence of communication: They are the building blocks of any language. Learning the meaning of words is thus one of the most important aspects of language acquisition: Children must first learn words before they can combine them into complex utterances. Many theories have been developed to explain the impressive efficiency of young children in acquiring the vocabulary of their language, as well as the developmental patterns observed in the course of lexical acquisition. A major source of disagreement among the different theories is whether children are equipped with special mechanisms and biases for word learning, or their general cognitive abilities are adequate for the task. We present a novel computational model of early word learning to shed light on the mechanisms that might be at work in this process. The model learns word meanings as probabilistic associations between words and semantic elements, using an incremental and probabilistic learning mechanism, and drawing only on general cognitive abilities. The results presented here demonstrate that much about word meanings can be learned from naturally occurring child‐directed utterances (paired with meaning representations), without using any special biases or constraints, and without any explicit developmental changes in the underlying learning mechanism. Furthermore, our model provides explanations for the occasionally contradictory child experimental data, and offers predictions for the behavior of young word learners in novel situations.
- 20 June 2007
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 41 (1) , 61-89
Automatically learning semantic knowledge about multiword predicates
- 20 June 2007
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 41 (1) , 61-89
Automatically learning semantic knowledge about multiword predicates
- 1 January 2007
- Published by Association for Computational Linguistics (ACL)
- p. 41-48
Pulling their weight
- 1 January 2007
- Published by Association for Computational Linguistics (ACL)
- p. 41-48
Pulling their weight
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
Learning Structured Appearance Models from Captioned Images of Cluttered Scenes
Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to learn both the names and appearances of the objects. Only a small number of local features within any given image are associated with a particular caption word. We describe a connected graph appearance model where vertices represent local features and edges encode spatial relationships. We use the repetition of feature neighborhoods across training images and a measure of correspondence with caption words to guide the search for meaningful feature configurations. We demonstrate improved results on a dataset to which an unstructured object model was previously applied. We also apply the new method to a more challenging collection of captioned images from the Web, detecting and annotating objects within highly cluttered realistic scenes.
- 1 January 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1-8
Learning Structured Appearance Models from Captioned Images of Cluttered Scenes
Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to learn both the names and appearances of the objects. Only a small number of local features within any given image are associated with a particular caption word. We describe a connected graph appearance model where vertices represent local features and edges encode spatial relationships. We use the repetition of feature neighborhoods across training images and a measure of correspondence with caption words to guide the search for meaningful feature configurations. We demonstrate improved results on a dataset to which an unstructured object model was previously applied. We also apply the new method to a more challenging collection of captioned images from the Web, detecting and annotating objects within highly cluttered realistic scenes.