@inproceedings{indig-etal-2020-xtsv,
title = "The xtsv Framework and the Twelve Virtues of Pipelines",
author = "Indig, Bal{\'a}zs and
Sass, B{\'a}lint and
Mittelholcz, Iv{\'a}n",
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-1.871",
pages = "7044--7052",
abstract = "We present xtsv, an abstract framework for building NLP pipelines. It covers several kinds of functionalities which can be implemented at an abstract level. We survey these features and argue that all are desired in a modern pipeline. The framework has a simple yet powerful internal communication format which is essentially tsv (tab separated values) with header plus some additional features. We put emphasis on the capabilities of the presented framework, for example its ability to allow new modules to be easily integrated or replaced, or the variety of its usage options. When a module is put into xtsv, all functionalities of the system are immediately available for that module, and the module can be be a part of an xtsv pipeline. The design also allows convenient investigation and manual correction of the data flow from one module to another. We demonstrate the power of our framework with a successful application: a concrete NLP pipeline for Hungarian called e-magyar text processing system (emtsv) which integrates Hungarian NLP tools in xtsv. All the advantages of the pipeline come from the inherent properties of the xtsv framework.",
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="indig-etal-2020-xtsv">
<titleInfo>
<title>The xtsv Framework and the Twelve Virtues of Pipelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Balázs</namePart>
<namePart type="family">Indig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bálint</namePart>
<namePart type="family">Sass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iván</namePart>
<namePart type="family">Mittelholcz</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>We present xtsv, an abstract framework for building NLP pipelines. It covers several kinds of functionalities which can be implemented at an abstract level. We survey these features and argue that all are desired in a modern pipeline. The framework has a simple yet powerful internal communication format which is essentially tsv (tab separated values) with header plus some additional features. We put emphasis on the capabilities of the presented framework, for example its ability to allow new modules to be easily integrated or replaced, or the variety of its usage options. When a module is put into xtsv, all functionalities of the system are immediately available for that module, and the module can be be a part of an xtsv pipeline. The design also allows convenient investigation and manual correction of the data flow from one module to another. We demonstrate the power of our framework with a successful application: a concrete NLP pipeline for Hungarian called e-magyar text processing system (emtsv) which integrates Hungarian NLP tools in xtsv. All the advantages of the pipeline come from the inherent properties of the xtsv framework.</abstract>
<identifier type="citekey">indig-etal-2020-xtsv</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.871</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7044</start>
<end>7052</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The xtsv Framework and the Twelve Virtues of Pipelines
%A Indig, Balázs
%A Sass, Bálint
%A Mittelholcz, Iván
%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 indig-etal-2020-xtsv
%X We present xtsv, an abstract framework for building NLP pipelines. It covers several kinds of functionalities which can be implemented at an abstract level. We survey these features and argue that all are desired in a modern pipeline. The framework has a simple yet powerful internal communication format which is essentially tsv (tab separated values) with header plus some additional features. We put emphasis on the capabilities of the presented framework, for example its ability to allow new modules to be easily integrated or replaced, or the variety of its usage options. When a module is put into xtsv, all functionalities of the system are immediately available for that module, and the module can be be a part of an xtsv pipeline. The design also allows convenient investigation and manual correction of the data flow from one module to another. We demonstrate the power of our framework with a successful application: a concrete NLP pipeline for Hungarian called e-magyar text processing system (emtsv) which integrates Hungarian NLP tools in xtsv. All the advantages of the pipeline come from the inherent properties of the xtsv framework.
%U https://aclanthology.org/2020.lrec-1.871
%P 7044-7052
Markdown (Informal)
[The xtsv Framework and the Twelve Virtues of Pipelines](https://aclanthology.org/2020.lrec-1.871) (Indig et al., LREC 2020)
ACL