A tabular method for dynamic oracles in transition-based parsing

Y. Goldberg; Francesco Sartorio; Giorgio Satta

A tabular method for dynamic oracles in transition-based parsing

Y. Goldberg
, Francesco Sartorio
, Giorgio Satta

Department of Computer Science and Artificial Intelligence

Bar-Ilan University

Research output: Contribution to journal › Article › peer-review

Abstract

We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles in training yields superior parsing accuracies on many languages.

Original language	English
Pages (from-to)	119-130
Number of pages	12
Journal	Transactions of the Association for Computational Linguistics
Volume	2
State	Published - 2014

Cite this

@article{2e7e40439fc642e6a278341154916ab6,

title = "A tabular method for dynamic oracles in transition-based parsing",

abstract = "We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles in training yields superior parsing accuracies on many languages.",

author = "Y. Goldberg and Francesco Sartorio and Giorgio Satta",

year = "2014",

language = "English",

volume = "2",

pages = "119--130",

journal = "Transactions of the Association for Computational Linguistics",

issn = "2307-387X",

publisher = "MIT Press",

}

TY - JOUR

T1 - A tabular method for dynamic oracles in transition-based parsing

AU - Goldberg, Y.

AU - Sartorio, Francesco

AU - Satta, Giorgio

PY - 2014

Y1 - 2014

N2 - We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles in training yields superior parsing accuracies on many languages.

AB - We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013). We experimentally show that using these oracles in training yields superior parsing accuracies on many languages.

UR - https://scholar.google.co.il/scholar?q=A+Tabular+Method+for+Dynamic+Oracles+in+Transition-Based+Parsing&btnG=&hl=en&as_sdt=0%2C5

M3 - Article

SN - 2307-387X

VL - 2

SP - 119

EP - 130

JO - Transactions of the Association for Computational Linguistics

JF - Transactions of the Association for Computational Linguistics

ER -

A tabular method for dynamic oracles in transition-based parsing

Abstract

Other files and links

Fingerprint

Cite this