@inproceedings{johansen-2019-named,
title = "Named-Entity Recognition for {N}orwegian",
author = "Johansen, Bjarte",
editor = "Hartmann, Mareike and
Plank, Barbara",
booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics",
month = sep # "{--}" # oct,
year = "2019",
address = "Turku, Finland",
publisher = {Link{\"o}ping University Electronic Press},
url = "https://aclanthology.org/W19-6123",
pages = "222--231",
abstract = "NER is the task of recognizing and demarcating the segments of a document that are part of a name and which type of name it is. We use 4 different categories of names: Locations (LOC), miscellaneous (MISC), organizations (ORG), and persons (PER). Even though we employ state of the art methods{---}including sub-word embeddings{---}that work well for English, we are unable to reproduce the same success for the Norwegian written forms. However, our model performs better than any previous research on Norwegian text. The study also presents the first NER for Nynorsk. Lastly, we find that by combining Nynorsk and Bokm{\aa}l into one training corpus we improve the performance of our model on both languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johansen-2019-named">
<titleInfo>
<title>Named-Entity Recognition for Norwegian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bjarte</namePart>
<namePart type="family">Johansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-sep–oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Nordic Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mareike</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press</publisher>
<place>
<placeTerm type="text">Turku, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NER is the task of recognizing and demarcating the segments of a document that are part of a name and which type of name it is. We use 4 different categories of names: Locations (LOC), miscellaneous (MISC), organizations (ORG), and persons (PER). Even though we employ state of the art methods—including sub-word embeddings—that work well for English, we are unable to reproduce the same success for the Norwegian written forms. However, our model performs better than any previous research on Norwegian text. The study also presents the first NER for Nynorsk. Lastly, we find that by combining Nynorsk and Bokmål into one training corpus we improve the performance of our model on both languages.</abstract>
<identifier type="citekey">johansen-2019-named</identifier>
<location>
<url>https://aclanthology.org/W19-6123</url>
</location>
<part>
<date>2019-sep–oct</date>
<extent unit="page">
<start>222</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named-Entity Recognition for Norwegian
%A Johansen, Bjarte
%Y Hartmann, Mareike
%Y Plank, Barbara
%S Proceedings of the 22nd Nordic Conference on Computational Linguistics
%D 2019
%8 sep–oct
%I Linköping University Electronic Press
%C Turku, Finland
%F johansen-2019-named
%X NER is the task of recognizing and demarcating the segments of a document that are part of a name and which type of name it is. We use 4 different categories of names: Locations (LOC), miscellaneous (MISC), organizations (ORG), and persons (PER). Even though we employ state of the art methods—including sub-word embeddings—that work well for English, we are unable to reproduce the same success for the Norwegian written forms. However, our model performs better than any previous research on Norwegian text. The study also presents the first NER for Nynorsk. Lastly, we find that by combining Nynorsk and Bokmål into one training corpus we improve the performance of our model on both languages.
%U https://aclanthology.org/W19-6123
%P 222-231
Markdown (Informal)
[Named-Entity Recognition for Norwegian](https://aclanthology.org/W19-6123) (Johansen, NoDaLiDa 2019)
ACL
- Bjarte Johansen. 2019. Named-Entity Recognition for Norwegian. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 222–231, Turku, Finland. Linköping University Electronic Press.