Easy-First Dependency Parsing of Modern Hebrew

Yoav Goldberg; Michael Elhadad

Easy-First Dependency Parsing of Modern Hebrew

Department of Computer Science

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

Abstract

We investigate the performance of an easy first, non-directional dependency parser on the Hebrew Dependency treebank. We show that with a basic feature set the greedy parser’s accuracy is on a par with that of a first-order globally optimized MST parser. The addition of morphological-agreement feature improves
the parsing accuracy, making it on-par with a second-order globally optimized MST parser. The improvement due to the morphological agreement information is persistent both when
gold-standard and automatically-induced morphological information is used.

Original language	English GB
Title of host publication	Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010
Editors	Djamé Seddah, Sandra Koebler, Reut Tsarfaty
Publisher	Association for Computational Linguistics
Pages	103-107
Number of pages	5
State	Published - 2010

Access to Document

https://www.aclweb.org/anthology/W10-1412/License: CC BY

Cite this

Goldberg, Y., & Elhadad, M. (2010). Easy-First Dependency Parsing of Modern Hebrew. In D. Seddah, S. Koebler, & R. Tsarfaty (Eds.), Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010 (pp. 103-107). Association for Computational Linguistics. https://www.aclweb.org/anthology/W10-1412/

@inproceedings{4684c8d38b0e4d6791238ad87fd2cedd,

title = "Easy-First Dependency Parsing of Modern Hebrew",

abstract = "We investigate the performance of an easy first, non-directional dependency parser on the Hebrew Dependency treebank. We show that with a basic feature set the greedy parser{\textquoteright}s accuracy is on a par with that of a first-order globally optimized MST parser. The addition of morphological-agreement feature improvesthe parsing accuracy, making it on-par with a second-order globally optimized MST parser. The improvement due to the morphological agreement information is persistent both whengold-standard and automatically-induced morphological information is used.",

author = "Yoav Goldberg and Michael Elhadad",

year = "2010",

language = "אנגלית",

pages = "103--107",

editor = "Djam{\'e} Seddah and Sandra Koebler and Reut Tsarfaty",

booktitle = "Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010",

publisher = "Association for Computational Linguistics",

}

Goldberg, Y & Elhadad, M 2010, Easy-First Dependency Parsing of Modern Hebrew. in D Seddah, S Koebler & R Tsarfaty (eds), Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010. Association for Computational Linguistics, pp. 103-107. <https://www.aclweb.org/anthology/W10-1412/>

Easy-First Dependency Parsing of Modern Hebrew. / Goldberg, Yoav; Elhadad, Michael.

Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010. ed. / Djamé Seddah; Sandra Koebler; Reut Tsarfaty. Association for Computational Linguistics, 2010. p. 103-107.

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

TY - GEN

T1 - Easy-First Dependency Parsing of Modern Hebrew

AU - Goldberg, Yoav

AU - Elhadad, Michael

PY - 2010

Y1 - 2010

N2 - We investigate the performance of an easy first, non-directional dependency parser on the Hebrew Dependency treebank. We show that with a basic feature set the greedy parser’s accuracy is on a par with that of a first-order globally optimized MST parser. The addition of morphological-agreement feature improvesthe parsing accuracy, making it on-par with a second-order globally optimized MST parser. The improvement due to the morphological agreement information is persistent both whengold-standard and automatically-induced morphological information is used.

AB - We investigate the performance of an easy first, non-directional dependency parser on the Hebrew Dependency treebank. We show that with a basic feature set the greedy parser’s accuracy is on a par with that of a first-order globally optimized MST parser. The addition of morphological-agreement feature improvesthe parsing accuracy, making it on-par with a second-order globally optimized MST parser. The improvement due to the morphological agreement information is persistent both whengold-standard and automatically-induced morphological information is used.

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

SP - 103

EP - 107

BT - Proceedings of the First Workshop on Statistical Parsing of Morphologically-Rich Languages, SPMRL@NAACL-HLT 2010, Los Angeles, CA, USA, June 5, 2010

A2 - Seddah, Djamé

A2 - Koebler, Sandra

A2 - Tsarfaty, Reut

PB - Association for Computational Linguistics

ER -