@inproceedings{schafer-2016-commoncow,
title = "{C}ommon{COW}: Massively Huge Web Corpora from {C}ommon{C}rawl Data and a Method to Distribute them Freely under Restrictive {EU} Copyright Laws",
author = {Sch{\"a}fer, Roland},
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1712",
pages = "4500--4504",
abstract = "In this paper, I describe a method of creating massively huge web corpora from the CommonCrawl data sets and redistributing the resulting annotations in a stand-off format. Current EU (and especially German) copyright legislation categorically forbids the redistribution of downloaded material without express prior permission by the authors. Therefore, such stand-off annotations (or other derivates) are the only format in which European researchers (like myself) are allowed to re-distribute the respective corpora. In order to make the full corpora available to the public despite such restrictions, the stand-off format presented here allows anybody to locally reconstruct the full corpora with the least possible computational effort.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schafer-2016-commoncow">
<titleInfo>
<title>CommonCOW: Massively Huge Web Corpora from CommonCrawl Data and a Method to Distribute them Freely under Restrictive EU Copyright Laws</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Schäfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, I describe a method of creating massively huge web corpora from the CommonCrawl data sets and redistributing the resulting annotations in a stand-off format. Current EU (and especially German) copyright legislation categorically forbids the redistribution of downloaded material without express prior permission by the authors. Therefore, such stand-off annotations (or other derivates) are the only format in which European researchers (like myself) are allowed to re-distribute the respective corpora. In order to make the full corpora available to the public despite such restrictions, the stand-off format presented here allows anybody to locally reconstruct the full corpora with the least possible computational effort.</abstract>
<identifier type="citekey">schafer-2016-commoncow</identifier>
<location>
<url>https://aclanthology.org/L16-1712</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>4500</start>
<end>4504</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CommonCOW: Massively Huge Web Corpora from CommonCrawl Data and a Method to Distribute them Freely under Restrictive EU Copyright Laws
%A Schäfer, Roland
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F schafer-2016-commoncow
%X In this paper, I describe a method of creating massively huge web corpora from the CommonCrawl data sets and redistributing the resulting annotations in a stand-off format. Current EU (and especially German) copyright legislation categorically forbids the redistribution of downloaded material without express prior permission by the authors. Therefore, such stand-off annotations (or other derivates) are the only format in which European researchers (like myself) are allowed to re-distribute the respective corpora. In order to make the full corpora available to the public despite such restrictions, the stand-off format presented here allows anybody to locally reconstruct the full corpora with the least possible computational effort.
%U https://aclanthology.org/L16-1712
%P 4500-4504
Markdown (Informal)
[CommonCOW: Massively Huge Web Corpora from CommonCrawl Data and a Method to Distribute them Freely under Restrictive EU Copyright Laws](https://aclanthology.org/L16-1712) (Schäfer, LREC 2016)
ACL