Hebrew dependency parsing: Initial results

Yoav Goldberg, Michael Elhadad

Research output: Contribution to conferencePaperpeer-review

12 Scopus citations

Abstract

We describe a newly available Hebrew Dependency Treebank, which is extracted from the Hebrew (constituency) Treebank. We establish some baseline unlabeled dependency parsing performance on Hebrew, based on two state-of-the-art parsers, MST-parser and MaltParser. The evaluation is performed both in an artificial setting, in which the data is assumed to be properly morphologically segmented and POS-tagged, and in a real-world setting, in which the parsing is performed on automatically segmented and POS-tagged text. We present an evaluation measure that takes into account the possibility of incompatible token segmentation between the gold standard and the parsed data. Results indicate that (a) MST-parser performs better on Hebrew data than MaltParser, and (b) both parsers do not make good use of morphological information when parsing Hebrew.

Original languageEnglish
Pages129-133
Number of pages5
StatePublished - 1 Jan 2009
Event11th International Conference on Parsing Technologies, IWPT 2009 - Paris, France
Duration: 7 Oct 20099 Oct 2009

Conference

Conference11th International Conference on Parsing Technologies, IWPT 2009
Country/TerritoryFrance
CityParis
Period7/10/099/10/09

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Hebrew dependency parsing: Initial results'. Together they form a unique fingerprint.

Cite this