Libby Barak

Learn More
Requiring only category names as user input is a highly attractive, yet hardly explored, setting for text categorization. Earlier bootstrap-ping results relied on similarity in LSA space, which captures rather coarse contextual similarity. We suggest improving this scheme by identifying concrete references to the category name's meaning, obtaining a special(More)
The acquisition of Belief verbs lags behind the acquisition of Desire verbs in children. Some psycholinguistic theories attribute this lag to conceptual differences between the two classes, while others suggest that syntactic differences are responsible. Through computational experiments , we show that a probabilistic verb learning model exhibits the(More)
The acquisition of Mental State Verbs (MSVs) has been extensively studied in respect to their common occurrence with sen-tential complement syntax. However, MSVs also occur in a variety of other syntactic structures. Moreover, other verb classes frequently occur with sentential complements, e.g., Communication and Perception verbs. The similarity in(More)
Using a computational model of verb argument structure learning , we study a key assumption of the usage-based theory: that the acquisition of a construction relies heavily on the existence of a high-frequency exemplar verb that accounts for a large proportion of usages of that construction in the input. Importantly , unlike the psycholinguistic experiments(More)
Natural language acquisition relies on appropriate generalization: the ability to produce novel sentences, while learning to restrict productions to acceptable forms in the language. Psycholinguists have proposed various properties that might play a role in guiding appropriate generalizations, looking at learning of verb alternations as a testbed. Several(More)
The acquisition of Belief verbs lags behind the acquisition of Desire verbs in children. Some psycholinguistic theories attribute this lag to conceptual differences between the two classes, while others suggest that syntactic differences are responsible. Through computational experiments , we show that a probabilistic verb learning model exhibits the(More)
ii Acknowledgements Many people have helped making the period of my Ph.D. studies successful and enjoyable and here I wish to express my gratitude to them. First and foremost, I would like to thank my advisor, Prof. Ido Dagan for his guidance and support during my graduate studies. Ido has been a role model and a source of inspiration in matters way beyond(More)