@inproceedings{kokkinakis-etal-2014-hfst,
title = "{HFST}-{S}we{NER} {---} A New {NER} Resource for {S}wedish",
author = "Kokkinakis, Dimitrios and
Niemi, Jyrki and
Hardwick, Sam and
Lind{\'e}n, Krister and
Borin, Lars",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/391_Paper.pdf",
pages = "2537--2543",
abstract = "Named entity recognition (NER) is a knowledge-intensive information extraction task that is used for recognizing textual mentions of entities that belong to a predefined set of categories, such as locations, organizations and time expressions. NER is a challenging, difficult, yet essential preprocessing technology for many natural language processing applications, and particularly crucial for language understanding. NER has been actively explored in academia and in industry especially during the last years due to the advent of social media data. This paper describes the conversion, modeling and adaptation of a Swedish NER system from a hybrid environment, with integrated functionality from various processing components, to the Helsinki Finite-State Transducer Technology (HFST) platform. This new HFST-based NER (HFST-SweNER) is a full-fledged open source implementation that supports a variety of generic named entity types and consists of multiple, reusable resource layers, e.g., various n-gram-based named entity lists (gazetteers).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kokkinakis-etal-2014-hfst">
<titleInfo>
<title>HFST-SweNER — A New NER Resource for Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Kokkinakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyrki</namePart>
<namePart type="family">Niemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Hardwick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krister</namePart>
<namePart type="family">Lindén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Borin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition (NER) is a knowledge-intensive information extraction task that is used for recognizing textual mentions of entities that belong to a predefined set of categories, such as locations, organizations and time expressions. NER is a challenging, difficult, yet essential preprocessing technology for many natural language processing applications, and particularly crucial for language understanding. NER has been actively explored in academia and in industry especially during the last years due to the advent of social media data. This paper describes the conversion, modeling and adaptation of a Swedish NER system from a hybrid environment, with integrated functionality from various processing components, to the Helsinki Finite-State Transducer Technology (HFST) platform. This new HFST-based NER (HFST-SweNER) is a full-fledged open source implementation that supports a variety of generic named entity types and consists of multiple, reusable resource layers, e.g., various n-gram-based named entity lists (gazetteers).</abstract>
<identifier type="citekey">kokkinakis-etal-2014-hfst</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/391_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2537</start>
<end>2543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HFST-SweNER — A New NER Resource for Swedish
%A Kokkinakis, Dimitrios
%A Niemi, Jyrki
%A Hardwick, Sam
%A Lindén, Krister
%A Borin, Lars
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F kokkinakis-etal-2014-hfst
%X Named entity recognition (NER) is a knowledge-intensive information extraction task that is used for recognizing textual mentions of entities that belong to a predefined set of categories, such as locations, organizations and time expressions. NER is a challenging, difficult, yet essential preprocessing technology for many natural language processing applications, and particularly crucial for language understanding. NER has been actively explored in academia and in industry especially during the last years due to the advent of social media data. This paper describes the conversion, modeling and adaptation of a Swedish NER system from a hybrid environment, with integrated functionality from various processing components, to the Helsinki Finite-State Transducer Technology (HFST) platform. This new HFST-based NER (HFST-SweNER) is a full-fledged open source implementation that supports a variety of generic named entity types and consists of multiple, reusable resource layers, e.g., various n-gram-based named entity lists (gazetteers).
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/391_Paper.pdf
%P 2537-2543
Markdown (Informal)
[HFST-SweNER — A New NER Resource for Swedish](http://www.lrec-conf.org/proceedings/lrec2014/pdf/391_Paper.pdf) (Kokkinakis et al., LREC 2014)
ACL
- Dimitrios Kokkinakis, Jyrki Niemi, Sam Hardwick, Krister Lindén, and Lars Borin. 2014. HFST-SweNER — A New NER Resource for Swedish. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2537–2543, Reykjavik, Iceland. European Language Resources Association (ELRA).