@inproceedings{fridriksdottir-etal-2022-building,
title = "Building an {I}celandic Entity Linking Corpus",
author = "Fri{\dh}riksd{\'o}ttir, Steinunn Rut and
Eggertsson, Valdimar {\'A}g{\'u}st and
J{\'o}hannesson, Benedikt Geir and
Dan{\'\i}elsson, Hjalti and
Loftsson, Hrafn and
Einarsson, Hafsteinn",
editor = {S{\"a}lev{\"a}, Jonne and
Lignos, Constantine},
booktitle = "Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.dclrl-1.4",
pages = "27--35",
abstract = "In this paper, we present the first Entity Linking corpus for Icelandic. We describe our approach of using a multilingual entity linking model (mGENRE) in combination with Wikipedia API Search (WAPIS) to label our data and compare it to an approach using WAPIS only. We find that our combined method reaches 53.9{\%} coverage on our corpus, compared to 30.9{\%} using only WAPIS. We analyze our results and explain the value of using a multilingual system when working with Icelandic. Additionally, we analyze the data that remain unlabeled, identify patterns and discuss why they may be more difficult to annotate.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fridriksdottir-etal-2022-building">
<titleInfo>
<title>Building an Icelandic Entity Linking Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steinunn</namePart>
<namePart type="given">Rut</namePart>
<namePart type="family">Fri\dhriksdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valdimar</namePart>
<namePart type="given">Ágúst</namePart>
<namePart type="family">Eggertsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benedikt</namePart>
<namePart type="given">Geir</namePart>
<namePart type="family">Jóhannesson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hjalti</namePart>
<namePart type="family">Daníelsson</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">Hafsteinn</namePart>
<namePart type="family">Einarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</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>
</relatedItem>
<abstract>In this paper, we present the first Entity Linking corpus for Icelandic. We describe our approach of using a multilingual entity linking model (mGENRE) in combination with Wikipedia API Search (WAPIS) to label our data and compare it to an approach using WAPIS only. We find that our combined method reaches 53.9% coverage on our corpus, compared to 30.9% using only WAPIS. We analyze our results and explain the value of using a multilingual system when working with Icelandic. Additionally, we analyze the data that remain unlabeled, identify patterns and discuss why they may be more difficult to annotate.</abstract>
<identifier type="citekey">fridriksdottir-etal-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.dclrl-1.4</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>27</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building an Icelandic Entity Linking Corpus
%A Fri\dhriksdóttir, Steinunn Rut
%A Eggertsson, Valdimar Ágúst
%A Jóhannesson, Benedikt Geir
%A Daníelsson, Hjalti
%A Loftsson, Hrafn
%A Einarsson, Hafsteinn
%Y Sälevä, Jonne
%Y Lignos, Constantine
%S Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F fridriksdottir-etal-2022-building
%X In this paper, we present the first Entity Linking corpus for Icelandic. We describe our approach of using a multilingual entity linking model (mGENRE) in combination with Wikipedia API Search (WAPIS) to label our data and compare it to an approach using WAPIS only. We find that our combined method reaches 53.9% coverage on our corpus, compared to 30.9% using only WAPIS. We analyze our results and explain the value of using a multilingual system when working with Icelandic. Additionally, we analyze the data that remain unlabeled, identify patterns and discuss why they may be more difficult to annotate.
%U https://aclanthology.org/2022.dclrl-1.4
%P 27-35
Markdown (Informal)
[Building an Icelandic Entity Linking Corpus](https://aclanthology.org/2022.dclrl-1.4) (Friðriksdóttir et al., DCLRL 2022)
ACL
- Steinunn Rut Friðriksdóttir, Valdimar Ágúst Eggertsson, Benedikt Geir Jóhannesson, Hjalti Daníelsson, Hrafn Loftsson, and Hafsteinn Einarsson. 2022. Building an Icelandic Entity Linking Corpus. In Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference, pages 27–35, Marseille, France. European Language Resources Association.