Inference of Inversion Transduction Grammars

Alexander Clark

Inference of Inversion Transduction Grammars

Alexander Clark

Philosophy

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

2 Citations (Scopus)

Abstract

We present the first polynomial algorithm for learning a class of inversion transduction grammars (ITGs) that implement context free transducers -- functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions.

These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under an identification in the limit model.

Original language	English
Title of host publication	Proceedings of The 28th International Conference on Machine Learning
Subtitle of host publication	ICML 2011
Editors	Lise Getoor, Tobias Scheffer
Place of Publication	Madison
Publisher	Madison : International Machine Learning Society
Pages	201-208
Number of pages	8
ISBN (Print)	9781450306195, 1450306195
Publication status	Published - 2011

Access to Document

http://www.icml-2011.org/papers/175_icmlpaper.pdf

Cite this

@inbook{3d0163df5f494ebfac935e397050d55c,

title = "Inference of Inversion Transduction Grammars",

abstract = "We present the first polynomial algorithm for learning a class of inversion transduction grammars (ITGs) that implement context free transducers -- functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions.These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under an identification in the limit model. ",

author = "Alexander Clark",

note = "Proceedings of the Twenty-eighth International Conference on Machine Learning : [Bellevue, Washington, USA, June 28 - July 2, 2011]",

year = "2011",

language = "English",

isbn = "9781450306195",

pages = "201--208",

editor = "Lise Getoor and Tobias Scheffer",

booktitle = "Proceedings of The 28th International Conference on Machine Learning",

publisher = "Madison : International Machine Learning Society",

}

TY - CHAP

T1 - Inference of Inversion Transduction Grammars

AU - Clark, Alexander

N1 - Proceedings of the Twenty-eighth International Conference on Machine Learning : [Bellevue, Washington, USA, June 28 - July 2, 2011]

PY - 2011

Y1 - 2011

N2 - We present the first polynomial algorithm for learning a class of inversion transduction grammars (ITGs) that implement context free transducers -- functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions.These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under an identification in the limit model.

AB - We present the first polynomial algorithm for learning a class of inversion transduction grammars (ITGs) that implement context free transducers -- functions from strings to strings. The class of transductions that we can learn properly includes all subsequential transductions.These algorithms are based on a generalisation of distributional learning; we prove correctness of our algorithm under an identification in the limit model.

M3 - Conference paper

SN - 9781450306195

SN - 1450306195

SP - 201

EP - 208

BT - Proceedings of The 28th International Conference on Machine Learning

A2 - Getoor, Lise

A2 - Scheffer, Tobias

PB - Madison : International Machine Learning Society

CY - Madison

ER -

Inference of Inversion Transduction Grammars

Abstract

Access to Document

Fingerprint

Cite this