@inproceedings{remus-biemann-2016-domain,
title = "Domain-Specific Corpus Expansion with Focused Webcrawling",
author = "Remus, Steffen and
Biemann, Chris",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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/L16-1572",
pages = "3607--3611",
abstract = "This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling. The focused webcrawler uses statistical N-gram language models to estimate the relatedness of documents and weblinks and needs as input only N-grams or plain texts of a predefined domain and seed URLs as starting points. Two experiments demonstrate that our focused crawler is able to stay focused in domain and language. The first experiment shows that the crawler stays in a focused domain, the second experiment demonstrates that language models trained on focused crawls obtain better perplexity scores on in-domain corpora. We distribute the focused crawler as open source software.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="remus-biemann-2016-domain">
<titleInfo>
<title>Domain-Specific Corpus Expansion with Focused Webcrawling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Remus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</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>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling. The focused webcrawler uses statistical N-gram language models to estimate the relatedness of documents and weblinks and needs as input only N-grams or plain texts of a predefined domain and seed URLs as starting points. Two experiments demonstrate that our focused crawler is able to stay focused in domain and language. The first experiment shows that the crawler stays in a focused domain, the second experiment demonstrates that language models trained on focused crawls obtain better perplexity scores on in-domain corpora. We distribute the focused crawler as open source software.</abstract>
<identifier type="citekey">remus-biemann-2016-domain</identifier>
<location>
<url>https://aclanthology.org/L16-1572</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3607</start>
<end>3611</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-Specific Corpus Expansion with Focused Webcrawling
%A Remus, Steffen
%A Biemann, Chris
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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 remus-biemann-2016-domain
%X This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling. The focused webcrawler uses statistical N-gram language models to estimate the relatedness of documents and weblinks and needs as input only N-grams or plain texts of a predefined domain and seed URLs as starting points. Two experiments demonstrate that our focused crawler is able to stay focused in domain and language. The first experiment shows that the crawler stays in a focused domain, the second experiment demonstrates that language models trained on focused crawls obtain better perplexity scores on in-domain corpora. We distribute the focused crawler as open source software.
%U https://aclanthology.org/L16-1572
%P 3607-3611
Markdown (Informal)
[Domain-Specific Corpus Expansion with Focused Webcrawling](https://aclanthology.org/L16-1572) (Remus & Biemann, LREC 2016)
ACL