@inproceedings{ahmadi-2020-klpt,
title = "{KLPT} {--} {K}urdish Language Processing Toolkit",
author = "Ahmadi, Sina",
editor = "Park, Eunjeong L. and
Hagiwara, Masato and
Milajevs, Dmitrijs and
Liu, Nelson F. and
Chauhan, Geeticka and
Tan, Liling",
booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlposs-1.11",
doi = "10.18653/v1/2020.nlposs-1.11",
pages = "72--84",
abstract = "Despite the recent advances in applying language-independent approaches to various natural language processing tasks thanks to artificial intelligence, some language-specific tools are still essential to process a language in a viable manner. Kurdish language is a less-resourced language with a remarkable diversity in dialects and scripts and lacks basic language processing tools. To address this issue, we introduce a language processing toolkit to handle such a diversity in an efficient way. Our toolkit is composed of fundamental components such as text preprocessing, stemming, tokenization, lemmatization and transliteration and is able to get further extended by future developers. The project is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmadi-2020-klpt">
<titleInfo>
<title>KLPT – Kurdish Language Processing Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Hagiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the recent advances in applying language-independent approaches to various natural language processing tasks thanks to artificial intelligence, some language-specific tools are still essential to process a language in a viable manner. Kurdish language is a less-resourced language with a remarkable diversity in dialects and scripts and lacks basic language processing tools. To address this issue, we introduce a language processing toolkit to handle such a diversity in an efficient way. Our toolkit is composed of fundamental components such as text preprocessing, stemming, tokenization, lemmatization and transliteration and is able to get further extended by future developers. The project is publicly available.</abstract>
<identifier type="citekey">ahmadi-2020-klpt</identifier>
<identifier type="doi">10.18653/v1/2020.nlposs-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.nlposs-1.11</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>72</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KLPT – Kurdish Language Processing Toolkit
%A Ahmadi, Sina
%Y Park, Eunjeong L.
%Y Hagiwara, Masato
%Y Milajevs, Dmitrijs
%Y Liu, Nelson F.
%Y Chauhan, Geeticka
%Y Tan, Liling
%S Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ahmadi-2020-klpt
%X Despite the recent advances in applying language-independent approaches to various natural language processing tasks thanks to artificial intelligence, some language-specific tools are still essential to process a language in a viable manner. Kurdish language is a less-resourced language with a remarkable diversity in dialects and scripts and lacks basic language processing tools. To address this issue, we introduce a language processing toolkit to handle such a diversity in an efficient way. Our toolkit is composed of fundamental components such as text preprocessing, stemming, tokenization, lemmatization and transliteration and is able to get further extended by future developers. The project is publicly available.
%R 10.18653/v1/2020.nlposs-1.11
%U https://aclanthology.org/2020.nlposs-1.11
%U https://doi.org/10.18653/v1/2020.nlposs-1.11
%P 72-84
Markdown (Informal)
[KLPT – Kurdish Language Processing Toolkit](https://aclanthology.org/2020.nlposs-1.11) (Ahmadi, NLPOSS 2020)
ACL