@inproceedings{jacquet-etal-2019-jrc,
title = "{JRC} {TMA}-{CC}: {S}lavic Named Entity Recognition and Linking. Participation in the {BSNLP}-2019 shared task",
author = "Jacquet, Guillaume and
Piskorski, Jakub and
Tanev, Hristo and
Steinberger, Ralf",
editor = "Erjavec, Toma{\v{z}} and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3714",
doi = "10.18653/v1/W19-3714",
pages = "100--104",
abstract = "We report on the participation of the JRC Text Mining and Analysis Competence Centre (TMA-CC) in the BSNLP-2019 Shared Task, which focuses on named-entity recognition, lemmatisation and cross-lingual linking. We propose a hybrid system combining a rule-based approach and light ML techniques. We use multilingual lexical resources such as JRC-NAMES and BABELNET together with a named entity guesser to recognise names. In a second step, we combine known names with wild cards to increase recognition recall by also capturing inflection variants. In a third step, we increase precision by filtering these name candidates with automatically learnt inflection patterns derived from name occurrences in large news article collections. Our major requirement is to achieve high precision. We achieved an average of 65{\%} F-measure with 93{\%} precision on the four languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacquet-etal-2019-jrc">
<titleInfo>
<title>JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in the BSNLP-2019 shared task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Jacquet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We report on the participation of the JRC Text Mining and Analysis Competence Centre (TMA-CC) in the BSNLP-2019 Shared Task, which focuses on named-entity recognition, lemmatisation and cross-lingual linking. We propose a hybrid system combining a rule-based approach and light ML techniques. We use multilingual lexical resources such as JRC-NAMES and BABELNET together with a named entity guesser to recognise names. In a second step, we combine known names with wild cards to increase recognition recall by also capturing inflection variants. In a third step, we increase precision by filtering these name candidates with automatically learnt inflection patterns derived from name occurrences in large news article collections. Our major requirement is to achieve high precision. We achieved an average of 65% F-measure with 93% precision on the four languages.</abstract>
<identifier type="citekey">jacquet-etal-2019-jrc</identifier>
<identifier type="doi">10.18653/v1/W19-3714</identifier>
<location>
<url>https://aclanthology.org/W19-3714</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>100</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in the BSNLP-2019 shared task
%A Jacquet, Guillaume
%A Piskorski, Jakub
%A Tanev, Hristo
%A Steinberger, Ralf
%Y Erjavec, Tomaž
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F jacquet-etal-2019-jrc
%X We report on the participation of the JRC Text Mining and Analysis Competence Centre (TMA-CC) in the BSNLP-2019 Shared Task, which focuses on named-entity recognition, lemmatisation and cross-lingual linking. We propose a hybrid system combining a rule-based approach and light ML techniques. We use multilingual lexical resources such as JRC-NAMES and BABELNET together with a named entity guesser to recognise names. In a second step, we combine known names with wild cards to increase recognition recall by also capturing inflection variants. In a third step, we increase precision by filtering these name candidates with automatically learnt inflection patterns derived from name occurrences in large news article collections. Our major requirement is to achieve high precision. We achieved an average of 65% F-measure with 93% precision on the four languages.
%R 10.18653/v1/W19-3714
%U https://aclanthology.org/W19-3714
%U https://doi.org/10.18653/v1/W19-3714
%P 100-104
Markdown (Informal)
[JRC TMA-CC: Slavic Named Entity Recognition and Linking. Participation in the BSNLP-2019 shared task](https://aclanthology.org/W19-3714) (Jacquet et al., BSNLP 2019)
ACL