@inproceedings{weichselbraun-etal-2019-improving,
title = "Improving Named Entity Linking Corpora Quality",
author = "Weichselbraun, Albert and
Brasoveanu, Adrian M.P. and
Kuntschik, Philipp and
Nixon, Lyndon J.B.",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1152",
doi = "10.26615/978-954-452-056-4_152",
pages = "1328--1337",
abstract = "Gold standard corpora and competitive evaluations play a key role in benchmarking named entity linking (NEL) performance and driving the development of more sophisticated NEL systems. The quality of the used corpora and the used evaluation metrics are crucial in this process. We, therefore, assess the quality of three popular evaluation corpora, identifying four major issues which affect these gold standards: (i) the use of different annotation styles, (ii) incorrect and missing annotations, (iii) Knowledge Base evolution, (iv) and differences in annotating co-occurrences. This paper addresses these issues by formalizing NEL annotations and corpus versioning which allows standardizing corpus creation, supports corpus evolution, and paves the way for the use of lenses to automatically transform between different corpus configurations. In addition, the use of clearly defined scoring rules and evaluation metrics ensures a better comparability of evaluation results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weichselbraun-etal-2019-improving">
<titleInfo>
<title>Improving Named Entity Linking Corpora Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Weichselbraun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="given">M.P.</namePart>
<namePart type="family">Brasoveanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Kuntschik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyndon</namePart>
<namePart type="given">J.B.</namePart>
<namePart type="family">Nixon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Gold standard corpora and competitive evaluations play a key role in benchmarking named entity linking (NEL) performance and driving the development of more sophisticated NEL systems. The quality of the used corpora and the used evaluation metrics are crucial in this process. We, therefore, assess the quality of three popular evaluation corpora, identifying four major issues which affect these gold standards: (i) the use of different annotation styles, (ii) incorrect and missing annotations, (iii) Knowledge Base evolution, (iv) and differences in annotating co-occurrences. This paper addresses these issues by formalizing NEL annotations and corpus versioning which allows standardizing corpus creation, supports corpus evolution, and paves the way for the use of lenses to automatically transform between different corpus configurations. In addition, the use of clearly defined scoring rules and evaluation metrics ensures a better comparability of evaluation results.</abstract>
<identifier type="citekey">weichselbraun-etal-2019-improving</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_152</identifier>
<location>
<url>https://aclanthology.org/R19-1152</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>1328</start>
<end>1337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Named Entity Linking Corpora Quality
%A Weichselbraun, Albert
%A Brasoveanu, Adrian M.P.
%A Kuntschik, Philipp
%A Nixon, Lyndon J.B.
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F weichselbraun-etal-2019-improving
%X Gold standard corpora and competitive evaluations play a key role in benchmarking named entity linking (NEL) performance and driving the development of more sophisticated NEL systems. The quality of the used corpora and the used evaluation metrics are crucial in this process. We, therefore, assess the quality of three popular evaluation corpora, identifying four major issues which affect these gold standards: (i) the use of different annotation styles, (ii) incorrect and missing annotations, (iii) Knowledge Base evolution, (iv) and differences in annotating co-occurrences. This paper addresses these issues by formalizing NEL annotations and corpus versioning which allows standardizing corpus creation, supports corpus evolution, and paves the way for the use of lenses to automatically transform between different corpus configurations. In addition, the use of clearly defined scoring rules and evaluation metrics ensures a better comparability of evaluation results.
%R 10.26615/978-954-452-056-4_152
%U https://aclanthology.org/R19-1152
%U https://doi.org/10.26615/978-954-452-056-4_152
%P 1328-1337
Markdown (Informal)
[Improving Named Entity Linking Corpora Quality](https://aclanthology.org/R19-1152) (Weichselbraun et al., RANLP 2019)
ACL
- Albert Weichselbraun, Adrian M.P. Brasoveanu, Philipp Kuntschik, and Lyndon J.B. Nixon. 2019. Improving Named Entity Linking Corpora Quality. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1328–1337, Varna, Bulgaria. INCOMA Ltd..