@inproceedings{zeng-etal-2020-cleek,
title = "{CLEEK}: A {C}hinese Long-text Corpus for Entity Linking",
author = "Zeng, Weixin and
Zhao, Xiang and
Tang, Jiuyang and
Tan, Zhen and
Huang, Xuqian",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.249",
pages = "2026--2035",
abstract = "Entity linking, as one of the fundamental tasks in natural language processing, is crucial to knowledge fusion, knowledge base construction and update. Nevertheless, in contrast to the research on entity linking for English text, which undergoes continuous development, the Chinese counterpart is still in its infancy. One prominent issue lies in publicly available annotated datasets and evaluation benchmarks, which are lacking and deficient. In specific, existing Chinese corpora for entity linking were mainly constructed from noisy short texts, such as microblogs and news headings, where long texts were largely overlooked, which yet constitute a wider spectrum of real-life scenarios. To address the issue, in this work, we build CLEEK, a Chinese corpus of multi-domain long text for entity linking, in order to encourage advancement of entity linking in languages besides English. The corpus consists of 100 documents from diverse domains, and is publicly accessible. Moreover, we devise a measure to evaluate the difficulty of documents with respect to entity linking, which is then used to characterize the corpus. Additionally, the results of two baselines and seven state-of-the-art solutions on CLEEK are reported and compared. The empirical results validate the usefulness of CLEEK and the effectiveness of proposed difficulty measure.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2020-cleek">
<titleInfo>
<title>CLEEK: A Chinese Long-text Corpus for Entity Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weixin</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiuyang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuqian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Entity linking, as one of the fundamental tasks in natural language processing, is crucial to knowledge fusion, knowledge base construction and update. Nevertheless, in contrast to the research on entity linking for English text, which undergoes continuous development, the Chinese counterpart is still in its infancy. One prominent issue lies in publicly available annotated datasets and evaluation benchmarks, which are lacking and deficient. In specific, existing Chinese corpora for entity linking were mainly constructed from noisy short texts, such as microblogs and news headings, where long texts were largely overlooked, which yet constitute a wider spectrum of real-life scenarios. To address the issue, in this work, we build CLEEK, a Chinese corpus of multi-domain long text for entity linking, in order to encourage advancement of entity linking in languages besides English. The corpus consists of 100 documents from diverse domains, and is publicly accessible. Moreover, we devise a measure to evaluate the difficulty of documents with respect to entity linking, which is then used to characterize the corpus. Additionally, the results of two baselines and seven state-of-the-art solutions on CLEEK are reported and compared. The empirical results validate the usefulness of CLEEK and the effectiveness of proposed difficulty measure.</abstract>
<identifier type="citekey">zeng-etal-2020-cleek</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.249</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2026</start>
<end>2035</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLEEK: A Chinese Long-text Corpus for Entity Linking
%A Zeng, Weixin
%A Zhao, Xiang
%A Tang, Jiuyang
%A Tan, Zhen
%A Huang, Xuqian
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F zeng-etal-2020-cleek
%X Entity linking, as one of the fundamental tasks in natural language processing, is crucial to knowledge fusion, knowledge base construction and update. Nevertheless, in contrast to the research on entity linking for English text, which undergoes continuous development, the Chinese counterpart is still in its infancy. One prominent issue lies in publicly available annotated datasets and evaluation benchmarks, which are lacking and deficient. In specific, existing Chinese corpora for entity linking were mainly constructed from noisy short texts, such as microblogs and news headings, where long texts were largely overlooked, which yet constitute a wider spectrum of real-life scenarios. To address the issue, in this work, we build CLEEK, a Chinese corpus of multi-domain long text for entity linking, in order to encourage advancement of entity linking in languages besides English. The corpus consists of 100 documents from diverse domains, and is publicly accessible. Moreover, we devise a measure to evaluate the difficulty of documents with respect to entity linking, which is then used to characterize the corpus. Additionally, the results of two baselines and seven state-of-the-art solutions on CLEEK are reported and compared. The empirical results validate the usefulness of CLEEK and the effectiveness of proposed difficulty measure.
%U https://aclanthology.org/2020.lrec-1.249
%P 2026-2035
Markdown (Informal)
[CLEEK: A Chinese Long-text Corpus for Entity Linking](https://aclanthology.org/2020.lrec-1.249) (Zeng et al., LREC 2020)
ACL
- Weixin Zeng, Xiang Zhao, Jiuyang Tang, Zhen Tan, and Xuqian Huang. 2020. CLEEK: A Chinese Long-text Corpus for Entity Linking. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2026–2035, Marseille, France. European Language Resources Association.