Language Acquisition and Probabilistic Models: keeping it simple
Aline Villavicencio, Marco Idiart, Robert Berwick and Igor Malioutov
The 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013)
Sofia, Bulgaria, August 4-9, 2013
Hierarchical Bayesian Models (HBMs) have been used with some success to capture empirically observed patterns of under- and overgeneralization in child language acquisition. However, as is well known, HBMs are ``ideal'' learning systems, assuming access to unlimited computational resources that may not be available to child language learners. Consequently, it remains crucial to carefully assess the use of HBMs along with alternative, possibly simpler, candidate models. This paper presents such an evaluation for a language acquisition domain where explicit HBMs have been proposed: the acquisition of English dative constructions. In particular, we present a detailed, empirically-grounded model-selection comparison of HBMs vs. a simpler alternative based on clustering along with maximum likelihood estimation that we call linear competition learning (LCL). Our results demonstrate that LCL can match HBM model performance without incurring on the high computational costs associated with HBMs.
Conference Manager (V2.61.0 - Rev. 2792M)