@inproceedings{oliver-mikelenic-2020-resipc,
title = "{R}e{S}i{PC}: a Tool for Complex Searches in Parallel Corpora",
author = "Oliver, Antoni and
Mikeleni{\'c}, Bojana",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.869",
pages = "7033--7037",
abstract = "In this paper, a tool specifically designed to allow for complex searches in large parallel corpora is presented. The formalism for the queries is very powerful as it uses standard regular expressions that allow for complex queries combining word forms, lemmata and POS-tags. As queries are performed over POS-tags, at least one of the languages in the parallel corpus should be POS-tagged. Searches can be performed in one of the languages or in both languages at the same time. The program is able to POS-tag the corpora using the Freeling analyzer through its Python API. ReSiPC is developed in Python version 3 and it is distributed under a free license (GNU GPL). The tool can be used to provide data for contrastive linguistics research and an example of use in a Spanish-Croatian parallel corpus is presented. ReSiPC is designed for queries in POS-tagged corpora, but it can be easily adapted for querying corpora containing other kinds of information.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oliver-mikelenic-2020-resipc">
<titleInfo>
<title>ReSiPC: a Tool for Complex Searches in Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoni</namePart>
<namePart type="family">Oliver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojana</namePart>
<namePart type="family">Mikelenić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, a tool specifically designed to allow for complex searches in large parallel corpora is presented. The formalism for the queries is very powerful as it uses standard regular expressions that allow for complex queries combining word forms, lemmata and POS-tags. As queries are performed over POS-tags, at least one of the languages in the parallel corpus should be POS-tagged. Searches can be performed in one of the languages or in both languages at the same time. The program is able to POS-tag the corpora using the Freeling analyzer through its Python API. ReSiPC is developed in Python version 3 and it is distributed under a free license (GNU GPL). The tool can be used to provide data for contrastive linguistics research and an example of use in a Spanish-Croatian parallel corpus is presented. ReSiPC is designed for queries in POS-tagged corpora, but it can be easily adapted for querying corpora containing other kinds of information.</abstract>
<identifier type="citekey">oliver-mikelenic-2020-resipc</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.869</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7033</start>
<end>7037</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReSiPC: a Tool for Complex Searches in Parallel Corpora
%A Oliver, Antoni
%A Mikelenić, Bojana
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F oliver-mikelenic-2020-resipc
%X In this paper, a tool specifically designed to allow for complex searches in large parallel corpora is presented. The formalism for the queries is very powerful as it uses standard regular expressions that allow for complex queries combining word forms, lemmata and POS-tags. As queries are performed over POS-tags, at least one of the languages in the parallel corpus should be POS-tagged. Searches can be performed in one of the languages or in both languages at the same time. The program is able to POS-tag the corpora using the Freeling analyzer through its Python API. ReSiPC is developed in Python version 3 and it is distributed under a free license (GNU GPL). The tool can be used to provide data for contrastive linguistics research and an example of use in a Spanish-Croatian parallel corpus is presented. ReSiPC is designed for queries in POS-tagged corpora, but it can be easily adapted for querying corpora containing other kinds of information.
%U https://aclanthology.org/2020.lrec-1.869
%P 7033-7037
Markdown (Informal)
[ReSiPC: a Tool for Complex Searches in Parallel Corpora](https://aclanthology.org/2020.lrec-1.869) (Oliver & Mikelenić, LREC 2020)
ACL