@inproceedings{garcia-duran-etal-2022-efficient,
title = "Efficient Entity Candidate Generation for Low-Resource Languages",
author = "Garcia-Duran, Alberto and
Arora, Akhil and
West, Robert",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.690",
pages = "6429--6438",
abstract = {Candidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Nevertheless, it has often been overlooked in the monolingual English entity linking literature, as na{\"\i}ve approaches obtain very good performance. Unfortunately, the existing approaches for English cannot be successfully transferred to poorly resourced languages. This paper constitutes an in-depth analysis of the candidate generation problem in the context of cross-lingual entity linking with a focus on low-resource languages. Among other contributions, we point out limitations in the evaluation conducted in previous works. We introduce a characterization of queries into types based on their difficulty, which improves the interpretability of the performance of different methods. We also propose a light-weight and simple solution based on the construction of indexes whose design is motivated by more complex transfer learning based neural approaches. A thorough empirical analysis on 9 real-world datasets under 2 evaluation settings shows that our simple solution outperforms the state-of-the-art approach in terms of both quality and efficiency for almost all datasets and query types.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-duran-etal-2022-efficient">
<titleInfo>
<title>Efficient Entity Candidate Generation for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Garcia-Duran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">West</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 Thirteenth 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">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>
</relatedItem>
<abstract>Candidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Nevertheless, it has often been overlooked in the monolingual English entity linking literature, as naïve approaches obtain very good performance. Unfortunately, the existing approaches for English cannot be successfully transferred to poorly resourced languages. This paper constitutes an in-depth analysis of the candidate generation problem in the context of cross-lingual entity linking with a focus on low-resource languages. Among other contributions, we point out limitations in the evaluation conducted in previous works. We introduce a characterization of queries into types based on their difficulty, which improves the interpretability of the performance of different methods. We also propose a light-weight and simple solution based on the construction of indexes whose design is motivated by more complex transfer learning based neural approaches. A thorough empirical analysis on 9 real-world datasets under 2 evaluation settings shows that our simple solution outperforms the state-of-the-art approach in terms of both quality and efficiency for almost all datasets and query types.</abstract>
<identifier type="citekey">garcia-duran-etal-2022-efficient</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.690</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6429</start>
<end>6438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Entity Candidate Generation for Low-Resource Languages
%A Garcia-Duran, Alberto
%A Arora, Akhil
%A West, Robert
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F garcia-duran-etal-2022-efficient
%X Candidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Nevertheless, it has often been overlooked in the monolingual English entity linking literature, as naïve approaches obtain very good performance. Unfortunately, the existing approaches for English cannot be successfully transferred to poorly resourced languages. This paper constitutes an in-depth analysis of the candidate generation problem in the context of cross-lingual entity linking with a focus on low-resource languages. Among other contributions, we point out limitations in the evaluation conducted in previous works. We introduce a characterization of queries into types based on their difficulty, which improves the interpretability of the performance of different methods. We also propose a light-weight and simple solution based on the construction of indexes whose design is motivated by more complex transfer learning based neural approaches. A thorough empirical analysis on 9 real-world datasets under 2 evaluation settings shows that our simple solution outperforms the state-of-the-art approach in terms of both quality and efficiency for almost all datasets and query types.
%U https://aclanthology.org/2022.lrec-1.690
%P 6429-6438
Markdown (Informal)
[Efficient Entity Candidate Generation for Low-Resource Languages](https://aclanthology.org/2022.lrec-1.690) (Garcia-Duran et al., LREC 2022)
ACL