Article Structure
Abstract
Hierarchical Bayesian Models (HBMs) have been used with some success to capture empirically observed patterns of under- and overgeneralization in child language acquisition.
Introduction
In recent years, with advances in probability and estimation theory, there has been much interest in Bayesian models (BMs) (Chater, Tenenbaum, and Yuille, 2006; Jones and Love, 2011) and their application to child language acquisition with its challenging com-
Evidence in Language Acquisition
A familiar problem for language acquisition is how children learn which verbs participate in so-called dative alternations, exemplified by the child-produced sentences 1 to 3, from the Brown (1973) corpus in CHILDES (MacWhin-ney, 1995).
Materials and Methods
3.1 Dative Corpora
Evaluation
The learning task consists of estimating the probability that a given verb occurs in a particular frame, using previous occurrences as the basis for this estimation.
Conclusions and Future Work
HBMs have been successfully used for a number of language acquisition tasks capturing both patterns of under- and overgeneralization found in child language acquisition.
Topics
language acquisition
- Hierarchical Bayesian Models (HBMs) have been used with some success to capture empirically observed patterns of under- and overgeneralization in child language acquisition .Page 1, “Abstract”
- This paper presents such an evaluation for a language acquisition domain where explicit HBMs have been proposed: the acquisition of English dative constructions.Page 1, “Abstract”
- In recent years, with advances in probability and estimation theory, there has been much interest in Bayesian models (BMs) (Chater, Tenenbaum, and Yuille, 2006; Jones and Love, 2011) and their application to child language acquisition with its challenging com-Page 1, “Introduction”
- In the case of many language acquisition tasks this behavior often takes the form of overgeneralization, but with eventual convergence to some target language given exposure to more data.Page 2, “Introduction”
- This paper is organized as follows: we start with a discussion of formalizations of language acquisition tasks, ยง2.Page 2, “Introduction”
- A familiar problem for language acquisition is how children learn which verbs participate in so-called dative alternations, exemplified by the child-produced sentences 1 to 3, from the Brown (1973) corpus in CHILDES (MacWhin-ney, 1995).Page 2, “Evidence in Language Acquisition”
- To emulate a child language acquisition environment we use naturalistic longitudinal child-directed data, from the Brown corpus in CHILDES, for one child (Adam) for a subset of 19 verbs in the DOD and PD verb frames, figure 1.Page 3, “Materials and Methods”
- HBMs have been successfully used for a number of language acquisition tasks capturing both patterns of under- and overgeneralization found in child language acquisition .Page 9, “Conclusions and Future Work”
See all papers in Proc. ACL 2013 that mention language acquisition.
See all papers in Proc. ACL that mention language acquisition.
Back to top.
gold standard
- Model comparison requires a gold standard database for acquisition, reporting which frames have been learned for which verbs at each stage, and how likely a child is of making creative uses of a particular verb in a new frame.Page 3, “Materials and Methods”
- An independent gold standard with developmental information (e.g.Page 3, “Materials and Methods”
- Therefore, the gold standard we use for evaluation is the classification predicted by Perfors, Tenenbaum, and Wonnacott (2010).Page 3, “Materials and Methods”
- To approximate the gold standard behavior of the HBM for this task (Perfors, Tenenbaum, and Wonnacott, 2010) we chose the following function for ac:Page 6, “Materials and Methods”
See all papers in Proc. ACL 2013 that mention gold standard.
See all papers in Proc. ACL that mention gold standard.
Back to top.
