University of Sussex
Browse
W98-1114.pdf (841.8 kB)

Can subcategorisation probabilities help a statistical parser?

Download (841.8 kB)
conference contribution
posted on 2023-06-07, 07:08 authored by John Carroll, Guido Minnen, Ted Briscoe
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.

History

Publication status

  • Published

File Version

  • Published version

Journal

Proceeding of the Sixth Workshop on Very Large Corpora

Publisher

Association for Computational Lingustics (ACL)

Page range

118-126

Event name

6th Workshop on Very Large Corpora, Montreal, Canada, 1998

Event location

Montreal, Canada

Event type

conference

Event date

15th - 16th August 1998

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Editors

Eugene Charniak

Legacy Posted Date

2020-06-01

First Open Access (FOA) Date

2023-05-04

First Compliant Deposit (FCD) Date

2020-06-01

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC