@inproceedings{ingolfsdottir-etal-2019-nefnir,
title = "{N}efnir: A high accuracy lemmatizer for {I}celandic",
author = "Ing{\'o}lfsd{\'o}ttir, Svanhv{\'\i}t Lilja and
Loftsson, Hrafn and
Da{\dh}ason, J{\'o}n Fri{\dh}rik and
Bjarnad{\'o}ttir, Krist{\'\i}n",
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/W19-6133",
pages = "310--315",
abstract = "Lemmatization, finding the basic morphological form of a word in a corpus, is an important step in many natural language processing tasks when working with morphologically rich languages. We describe and evaluate Nefnir, a new open source lemmatizer for Icelandic. Nefnir uses suffix substitution rules, derived from a large morphological database, to lemmatize tagged text. Evaluation shows that for correctly tagged text, Nefnir obtains an accuracy of 99.55{\%}, and for text tagged with a PoS tagger, the accuracy obtained is 96.88{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ingolfsdottir-etal-2019-nefnir">
<titleInfo>
<title>Nefnir: A high accuracy lemmatizer for Icelandic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svanhvít</namePart>
<namePart type="given">Lilja</namePart>
<namePart type="family">Ingólfsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="given">Fri\dhrik</namePart>
<namePart type="family">Da\dhason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristín</namePart>
<namePart type="family">Bjarnadóttir</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>Lemmatization, finding the basic morphological form of a word in a corpus, is an important step in many natural language processing tasks when working with morphologically rich languages. We describe and evaluate Nefnir, a new open source lemmatizer for Icelandic. Nefnir uses suffix substitution rules, derived from a large morphological database, to lemmatize tagged text. Evaluation shows that for correctly tagged text, Nefnir obtains an accuracy of 99.55%, and for text tagged with a PoS tagger, the accuracy obtained is 96.88%.</abstract>
<identifier type="citekey">ingolfsdottir-etal-2019-nefnir</identifier>
<location>
<url>https://aclanthology.org/W19-6133</url>
</location>
<part>
<date>2019-sep–oct</date>
<extent unit="page">
<start>310</start>
<end>315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nefnir: A high accuracy lemmatizer for Icelandic
%A Ingólfsdóttir, Svanhvít Lilja
%A Loftsson, Hrafn
%A Da\dhason, Jón Fri\dhrik
%A Bjarnadóttir, Kristín
%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 ingolfsdottir-etal-2019-nefnir
%X Lemmatization, finding the basic morphological form of a word in a corpus, is an important step in many natural language processing tasks when working with morphologically rich languages. We describe and evaluate Nefnir, a new open source lemmatizer for Icelandic. Nefnir uses suffix substitution rules, derived from a large morphological database, to lemmatize tagged text. Evaluation shows that for correctly tagged text, Nefnir obtains an accuracy of 99.55%, and for text tagged with a PoS tagger, the accuracy obtained is 96.88%.
%U https://aclanthology.org/W19-6133
%P 310-315
Markdown (Informal)
[Nefnir: A high accuracy lemmatizer for Icelandic](https://aclanthology.org/W19-6133) (Ingólfsdóttir et al., NoDaLiDa 2019)
ACL
- Svanhvít Lilja Ingólfsdóttir, Hrafn Loftsson, Jón Friðrik Daðason, and Kristín Bjarnadóttir. 2019. Nefnir: A high accuracy lemmatizer for Icelandic. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 310–315, Turku, Finland. Linköping University Electronic Press.