License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.SLATE.2017.19
URN: urn:nbn:de:0030-drops-79525
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2017/7952/
Go to the corresponding OASIcs Volume Portal

Hassani, Hossein

A Method for Proper Noun Extraction in Kurdish

pdf-format:
OASIcs-SLATE-2017-19.pdf (0.1 MB)

Abstract

This paper suggests a method for proper noun identification in Kurdish texts. Kurdish proper nouns are not capitalized and they also assume other part-of-speech roles, which leads to a broad ambiguity that should be addressed in Kurdish proper noun recognition applications. Kurdish is also among less-resourced languages. We developed an application based on an architecture which includes a number of name lists, a set of rules, and a set of processes that recognizes Kurdish person names. This can help the study of Information Retrieval (IR) in Kurdish to advance and can also be used in Kurdish machine translation. We conducted several experiments which showed that the precision of the method is more than 95%, the recall is between 40% to 80%, and the F-measure is close to 60% to more than 80%. The reason for the low recall precision was because our name lists were not exhaustive enough to cover the vast majority of the Kurdish names.

BibTeX - Entry

@InProceedings{hassani:OASIcs:2017:7952,
  author =	{Hossein Hassani},
  title =	{{A Method for Proper Noun Extraction in Kurdish}},
  booktitle =	{6th Symposium on Languages, Applications and Technologies (SLATE 2017)},
  pages =	{19:1--19:13},
  series =	{OpenAccess Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-056-9},
  ISSN =	{2190-6807},
  year =	{2017},
  volume =	{56},
  editor =	{Ricardo Queir{\'o}s and M{\'a}rio Pinto and Alberto Sim{\~o}es and Jos{\'e} Paulo Leal and Maria Jo{\~a}o Varanda},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2017/7952},
  URN =		{urn:nbn:de:0030-drops-79525},
  doi =		{10.4230/OASIcs.SLATE.2017.19},
  annote =	{Keywords: Proper Noun Recognition, Named Entity Recognition, Information Extraction, Natural Language Processing, Kurdish}
}

Keywords: Proper Noun Recognition, Named Entity Recognition, Information Extraction, Natural Language Processing, Kurdish
Collection: 6th Symposium on Languages, Applications and Technologies (SLATE 2017)
Issue Date: 2017
Date of publication: 04.10.2017

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI