Brunel University Research Archive (BURA) >
Research Areas >
Psychology >

Please use this identifier to cite or link to this item:

Title: Resolving ambiguities in the extraction of syntactic categories through chunking.
Authors: Freudenthal, D
Pine, J M
Gobet, F
Keywords: co-occurrence statistics
language acquisition
child language
computational modelling
subject omission
Publication Date: 2004
Publisher: Proceedings of the Sixth International Conference on Cognitive Modeling
Citation: Freudenthal, D., Pine, J. M., & Gobet, F. (2004). Resolving ambiguities in the extraction of syntactic categories through chunking. Proceedings of the Sixth International Conference on Cognitive Modeling (pp. 94-99). Mahwah, NJ: Erlbaum.
Abstract: In recent years, several authors have investigated how co-occurrence statistics in natural language can act as a cue that children may use to extract syntactic categories for the language they are learning. While some authors have reported encouraging results, it is difficult to evaluate the quality of the syntactic categories derived. It is argued in this paper that traditional measures of accuracy are inherently flawed. A valid evaluation metric needs to consider the well-formedness of utterances generated through a production end. This paper attempts to evaluate the quality of the categories derived from cooccurrence statistics through the use of MOSAIC, a computational model of syntax acquisition that has already been used to simulate several phenomena in child language. It will be shown that derived syntactic categories which may appear to be of high quality will quickly give rise to errors which are not typical of child speech. A solution to this problem is suggested in the form of a chunking mechanism which serves to differentiate between alternative grammatical functions of identical word forms. Results are evaluated in terms of the error rates in utterances produced by the system as well as the quantitative fit to the phenomenon of subject omission.
Appears in Collections:School of Social Sciences Research Papers

Files in This Item:

File Description SizeFormat
Resolving ambiguities.pdf182.14 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.


Library (c) Brunel University.    Powered By: DSpace
Send us your
Feedback. Last Updated: September 14, 2010.
Managed by:
Hassan Bhuiyan