Can subcategorisation probabilities help a statistical parser?

Carroll, John, Minnen, Guido and Briscoe, Ted (1998) Can subcategorisation probabilities help a statistical parser? 6th Workshop on Very Large Corpora, Montreal, Canada, 1998, Montreal, Canada, 15th - 16th August 1998. Published in: Charniak, Eugene, (ed.) Proceeding of the Sixth Workshop on Very Large Corpora. 118-126. Association for Computational Lingustics (ACL)

[img] PDF - Other
Restricted to SRO admin only

Download (138kB)
[img] PDF - Published Version
Restricted to SRO admin only
Available under License Creative Commons Attribution-Non-Commercial.

Download (862kB)

Abstract

Research into the automatic acquisition of lexical information from corpora is starting to produce large-scale computational lexicons containing data on the relative frequencies of subcategorisation alternatives for individual verbal predicates. However, the empirical question of whether this type of frequency information can in practice improve the accuracy of a statistical parser has not yet been answered. In this paper we describe an experiment with a wide-coverage statistical grammar and parser for English and subcategorisation frequencies acquired from ten million words of text which shows that this information can significantly improve parse accuracy.

Item Type: Conference Proceedings
Keywords: cmp-lg, cmp-lg, cs.CL
Schools and Departments: School of Engineering and Informatics > Informatics
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 01 Jun 2020 07:58
Last Modified: 01 Jun 2020 07:58
URI: http://sro.sussex.ac.uk/id/eprint/91500

View download statistics for this item

📧 Request an update