@inproceedings{alves-etal-2020-natural,
title = "Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for {E}uropean {U}nion Under-resourced Languages",
author = "Alves, Diego and
Thakkar, Gaurish and
Tadi{\'c}, Marko",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.21/",
pages = "153--158",
language = "eng",
ISBN = "979-10-95546-35-1",
abstract = "This article presents the strategy for developing a platform containing Language Processing Chains for European Union languages, consisting of Tokenization to Parsing, also including Named Entity recognition and with addition of Sentiment Analysis. These chains are part of the first step of an event-centric knowledge processing pipeline whose aim is to process multilingual media information about major events that can cause an impact in Europe and the rest of the world. Due to the differences in terms of availability of language resources for each language, we have built this strategy in three steps, starting with processing chains for the well-resourced languages and finishing with the development of new modules for the under-resourced ones. In order to classify all European Union official languages in terms of resources, we have analysed the size of annotated corpora as well as the existence of pre-trained models in mainstream Language Processing tools, and we have combined this information with the proposed classification published at META-NET whitepaper series."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alves-etal-2020-natural">
<titleInfo>
<title>Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union 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">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</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">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>This article presents the strategy for developing a platform containing Language Processing Chains for European Union languages, consisting of Tokenization to Parsing, also including Named Entity recognition and with addition of Sentiment Analysis. These chains are part of the first step of an event-centric knowledge processing pipeline whose aim is to process multilingual media information about major events that can cause an impact in Europe and the rest of the world. Due to the differences in terms of availability of language resources for each language, we have built this strategy in three steps, starting with processing chains for the well-resourced languages and finishing with the development of new modules for the under-resourced ones. In order to classify all European Union official languages in terms of resources, we have analysed the size of annotated corpora as well as the existence of pre-trained models in mainstream Language Processing tools, and we have combined this information with the proposed classification published at META-NET whitepaper series.</abstract>
<identifier type="citekey">alves-etal-2020-natural</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.21/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>153</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-resourced Languages
%A Alves, Diego
%A Thakkar, Gaurish
%A Tadić, Marko
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G eng
%F alves-etal-2020-natural
%X This article presents the strategy for developing a platform containing Language Processing Chains for European Union languages, consisting of Tokenization to Parsing, also including Named Entity recognition and with addition of Sentiment Analysis. These chains are part of the first step of an event-centric knowledge processing pipeline whose aim is to process multilingual media information about major events that can cause an impact in Europe and the rest of the world. Due to the differences in terms of availability of language resources for each language, we have built this strategy in three steps, starting with processing chains for the well-resourced languages and finishing with the development of new modules for the under-resourced ones. In order to classify all European Union official languages in terms of resources, we have analysed the size of annotated corpora as well as the existence of pre-trained models in mainstream Language Processing tools, and we have combined this information with the proposed classification published at META-NET whitepaper series.
%U https://aclanthology.org/2020.sltu-1.21/
%P 153-158
Markdown (Informal)
[Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-resourced Languages](https://aclanthology.org/2020.sltu-1.21/) (Alves et al., SLTU 2020)
ACL