More for less: Learning a wide covering grammar from a small trainingset

Miles Osborne; Derek Bridge

More for less: Learning a wide covering grammar from a small trainingset

Miles Osborne
, Derek Bridge

University of York

Research output: Chapter in Book/Report/Conference proceedings › Chapter › peer-review

Abstract

In this paper, we present some results of our grammar learning system. We show that using unification-based grammars with a hybrid learning system allows a rapid rate of convergence upon a test corpus with only a modest amount of training material.

Original language	English
Title of host publication	New Methods In Language Processing
Publisher	Taylor and Francis
Pages	344-354
Number of pages	11
ISBN (Electronic)	9781134227389
ISBN (Print)	9781315072685
Publication status	Published - 1 Jan 2013
Externally published	Yes

Cite this

@inbook{291a20190a1245b5b92ccaeb6ebb5232,

title = "More for less: Learning a wide covering grammar from a small trainingset",

abstract = "In this paper, we present some results of our grammar learning system. We show that using unification-based grammars with a hybrid learning system allows a rapid rate of convergence upon a test corpus with only a modest amount of training material.",

author = "Miles Osborne and Derek Bridge",

note = "Publisher Copyright: {\textcopyright} D.B. Jones, H.L. Somers and contributors 1997.",

year = "2013",

month = jan,

day = "1",

language = "English",

isbn = "9781315072685",

pages = "344--354",

booktitle = "New Methods In Language Processing",

publisher = "Taylor and Francis",

address = "Australia",

}

TY - CHAP

T1 - More for less

T2 - Learning a wide covering grammar from a small trainingset

AU - Osborne, Miles

AU - Bridge, Derek

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In this paper, we present some results of our grammar learning system. We show that using unification-based grammars with a hybrid learning system allows a rapid rate of convergence upon a test corpus with only a modest amount of training material.

AB - In this paper, we present some results of our grammar learning system. We show that using unification-based grammars with a hybrid learning system allows a rapid rate of convergence upon a test corpus with only a modest amount of training material.

UR - https://www.scopus.com/pages/publications/85137444291

M3 - Chapter

AN - SCOPUS:85137444291

SN - 9781315072685

SP - 344

EP - 354

BT - New Methods In Language Processing

PB - Taylor and Francis

ER -

More for less: Learning a wide covering grammar from a small trainingset

Abstract

Other files and links

Fingerprint

Cite this