@inproceedings{alves-etal-2020-evaluating,
title = "Evaluating Language Tools for Fifteen {EU}-official Under-resourced Languages",
author = "Alves, Diego and
Thakkar, Gaurish and
Tadi{\'c}, Marko",
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-1.230",
pages = "1866--1873",
abstract = "This article presents the results of the evaluation campaign of language tools available for fifteen EU-official under-resourced languages. The evaluation was conducted within the MSC ITN CLEOPATRA action that aims at building the cross-lingual event-centric knowledge processing on top of the application of linguistic processing chains (LPCs) for at least 24 EU-official languages. In this campaign, we concentrated on three existing NLP platforms (Stanford CoreNLP, NLP Cube, UDPipe) that all provide models for under-resourced languages and in this first run we covered 15 under-resourced languages for which the models were available. We present the design of the evaluation campaign and present the results as well as discuss them. We considered the difference between reported and our tested results within a single percentage point as being within the limits of acceptable tolerance and thus consider this result as reproducible. However, for a number of languages, the results are below what was reported in the literature, and in some cases, our testing results are even better than the ones reported previously. Particularly problematic was the evaluation of NERC systems. One of the reasons is the absence of universally or cross-lingually applicable named entities classification scheme that would serve the NERC task in different languages analogous to the Universal Dependency scheme in parsing task. To build such a scheme has become one of our the future research directions.",
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="alves-etal-2020-evaluating">
<titleInfo>
<title>Evaluating Language Tools for Fifteen EU-official Under-resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Alves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurish</namePart>
<namePart type="family">Thakkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Tadić</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>This article presents the results of the evaluation campaign of language tools available for fifteen EU-official under-resourced languages. The evaluation was conducted within the MSC ITN CLEOPATRA action that aims at building the cross-lingual event-centric knowledge processing on top of the application of linguistic processing chains (LPCs) for at least 24 EU-official languages. In this campaign, we concentrated on three existing NLP platforms (Stanford CoreNLP, NLP Cube, UDPipe) that all provide models for under-resourced languages and in this first run we covered 15 under-resourced languages for which the models were available. We present the design of the evaluation campaign and present the results as well as discuss them. We considered the difference between reported and our tested results within a single percentage point as being within the limits of acceptable tolerance and thus consider this result as reproducible. However, for a number of languages, the results are below what was reported in the literature, and in some cases, our testing results are even better than the ones reported previously. Particularly problematic was the evaluation of NERC systems. One of the reasons is the absence of universally or cross-lingually applicable named entities classification scheme that would serve the NERC task in different languages analogous to the Universal Dependency scheme in parsing task. To build such a scheme has become one of our the future research directions.</abstract>
<identifier type="citekey">alves-etal-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.230</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1866</start>
<end>1873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Language Tools for Fifteen EU-official Under-resourced Languages
%A Alves, Diego
%A Thakkar, Gaurish
%A Tadić, Marko
%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 alves-etal-2020-evaluating
%X This article presents the results of the evaluation campaign of language tools available for fifteen EU-official under-resourced languages. The evaluation was conducted within the MSC ITN CLEOPATRA action that aims at building the cross-lingual event-centric knowledge processing on top of the application of linguistic processing chains (LPCs) for at least 24 EU-official languages. In this campaign, we concentrated on three existing NLP platforms (Stanford CoreNLP, NLP Cube, UDPipe) that all provide models for under-resourced languages and in this first run we covered 15 under-resourced languages for which the models were available. We present the design of the evaluation campaign and present the results as well as discuss them. We considered the difference between reported and our tested results within a single percentage point as being within the limits of acceptable tolerance and thus consider this result as reproducible. However, for a number of languages, the results are below what was reported in the literature, and in some cases, our testing results are even better than the ones reported previously. Particularly problematic was the evaluation of NERC systems. One of the reasons is the absence of universally or cross-lingually applicable named entities classification scheme that would serve the NERC task in different languages analogous to the Universal Dependency scheme in parsing task. To build such a scheme has become one of our the future research directions.
%U https://aclanthology.org/2020.lrec-1.230
%P 1866-1873
Markdown (Informal)
[Evaluating Language Tools for Fifteen EU-official Under-resourced Languages](https://aclanthology.org/2020.lrec-1.230) (Alves et al., LREC 2020)
ACL