@inproceedings{ljubesic-etal-2016-producing,
title = "Producing Monolingual and Parallel Web Corpora at the Same Time - {S}pider{L}ing and Bitextor{'}s Love Affair",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Espl{\`a}-Gomis, Miquel and
Toral, Antonio and
Rojas, Sergio Ortiz and
Klubi{\v{c}}ka, Filip",
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/L16-1471",
pages = "2949--2956",
abstract = "This paper presents an approach for building large monolingual corpora and, at the same time, extracting parallel data by crawling the top-level domain of a given language of interest. For gathering linguistically relevant data from top-level domains we use the SpiderLing crawler, modified to crawl data written in multiple languages. The output of this process is then fed to Bitextor, a tool for harvesting parallel data from a collection of documents. We call the system combining these two tools Spidextor, a blend of the names of its two crucial parts. We evaluate the described approach intrinsically by measuring the accuracy of the extracted bitexts from the Croatian top-level domain {``}.hr{''} and the Slovene top-level domain {``}.si{''}, and extrinsically on the English-Croatian language pair by comparing an SMT system built from the crawled data with third-party systems. We finally present parallel datasets collected with our approach for the English-Croatian, English-Finnish, English-Serbian and English-Slovene language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2016-producing">
<titleInfo>
<title>Producing Monolingual and Parallel Web Corpora at the Same Time - SpiderLing and Bitextor’s Love Affair</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miquel</namePart>
<namePart type="family">Esplà-Gomis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="given">Ortiz</namePart>
<namePart type="family">Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Klubička</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>This paper presents an approach for building large monolingual corpora and, at the same time, extracting parallel data by crawling the top-level domain of a given language of interest. For gathering linguistically relevant data from top-level domains we use the SpiderLing crawler, modified to crawl data written in multiple languages. The output of this process is then fed to Bitextor, a tool for harvesting parallel data from a collection of documents. We call the system combining these two tools Spidextor, a blend of the names of its two crucial parts. We evaluate the described approach intrinsically by measuring the accuracy of the extracted bitexts from the Croatian top-level domain “.hr” and the Slovene top-level domain “.si”, and extrinsically on the English-Croatian language pair by comparing an SMT system built from the crawled data with third-party systems. We finally present parallel datasets collected with our approach for the English-Croatian, English-Finnish, English-Serbian and English-Slovene language pairs.</abstract>
<identifier type="citekey">ljubesic-etal-2016-producing</identifier>
<location>
<url>https://aclanthology.org/L16-1471</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>2949</start>
<end>2956</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Producing Monolingual and Parallel Web Corpora at the Same Time - SpiderLing and Bitextor’s Love Affair
%A Ljubešić, Nikola
%A Esplà-Gomis, Miquel
%A Toral, Antonio
%A Rojas, Sergio Ortiz
%A Klubička, Filip
%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 ljubesic-etal-2016-producing
%X This paper presents an approach for building large monolingual corpora and, at the same time, extracting parallel data by crawling the top-level domain of a given language of interest. For gathering linguistically relevant data from top-level domains we use the SpiderLing crawler, modified to crawl data written in multiple languages. The output of this process is then fed to Bitextor, a tool for harvesting parallel data from a collection of documents. We call the system combining these two tools Spidextor, a blend of the names of its two crucial parts. We evaluate the described approach intrinsically by measuring the accuracy of the extracted bitexts from the Croatian top-level domain “.hr” and the Slovene top-level domain “.si”, and extrinsically on the English-Croatian language pair by comparing an SMT system built from the crawled data with third-party systems. We finally present parallel datasets collected with our approach for the English-Croatian, English-Finnish, English-Serbian and English-Slovene language pairs.
%U https://aclanthology.org/L16-1471
%P 2949-2956
Markdown (Informal)
[Producing Monolingual and Parallel Web Corpora at the Same Time - SpiderLing and Bitextor’s Love Affair](https://aclanthology.org/L16-1471) (Ljubešić et al., LREC 2016)
ACL