@inproceedings{nothman-etal-2018-stop,
title = "Stop Word Lists in Free Open-source Software Packages",
author = "Nothman, Joel and
Qin, Hanmin and
Yurchak, Roman",
editor = "Park, Eunjeong L. and
Hagiwara, Masato and
Milajevs, Dmitrijs and
Tan, Liling",
booktitle = "Proceedings of Workshop for {NLP} Open Source Software ({NLP}-{OSS})",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-2502",
doi = "10.18653/v1/W18-2502",
pages = "7--12",
abstract = "Open-source software packages for language processing often include stop word lists. Users may apply them without awareness of their surprising omissions (e.g. {``}hasn{'}t{''} but not {``}hadn{'}t{''}) and inclusions ({``}computer{''}), or their incompatibility with a particular tokenizer. Motivated by issues raised about the Scikit-learn stop list, we investigate variation among and consistency within 52 popular English-language stop lists, and propose strategies for mitigating these issues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nothman-etal-2018-stop">
<titleInfo>
<title>Stop Word Lists in Free Open-source Software Packages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Nothman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanmin</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yurchak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of 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">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">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open-source software packages for language processing often include stop word lists. Users may apply them without awareness of their surprising omissions (e.g. “hasn’t” but not “hadn’t”) and inclusions (“computer”), or their incompatibility with a particular tokenizer. Motivated by issues raised about the Scikit-learn stop list, we investigate variation among and consistency within 52 popular English-language stop lists, and propose strategies for mitigating these issues.</abstract>
<identifier type="citekey">nothman-etal-2018-stop</identifier>
<identifier type="doi">10.18653/v1/W18-2502</identifier>
<location>
<url>https://aclanthology.org/W18-2502</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>7</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stop Word Lists in Free Open-source Software Packages
%A Nothman, Joel
%A Qin, Hanmin
%A Yurchak, Roman
%Y Park, Eunjeong L.
%Y Hagiwara, Masato
%Y Milajevs, Dmitrijs
%Y Tan, Liling
%S Proceedings of Workshop for NLP Open Source Software (NLP-OSS)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F nothman-etal-2018-stop
%X Open-source software packages for language processing often include stop word lists. Users may apply them without awareness of their surprising omissions (e.g. “hasn’t” but not “hadn’t”) and inclusions (“computer”), or their incompatibility with a particular tokenizer. Motivated by issues raised about the Scikit-learn stop list, we investigate variation among and consistency within 52 popular English-language stop lists, and propose strategies for mitigating these issues.
%R 10.18653/v1/W18-2502
%U https://aclanthology.org/W18-2502
%U https://doi.org/10.18653/v1/W18-2502
%P 7-12
Markdown (Informal)
[Stop Word Lists in Free Open-source Software Packages](https://aclanthology.org/W18-2502) (Nothman et al., NLPOSS 2018)
ACL