@inproceedings{dunn-etal-2022-predicting,
title = "Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures",
author = "Dunn, Jonathan and
Li, Haipeng and
Sastre, Damian",
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-1.693",
pages = "6461--6470",
abstract = "This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible to estimate the reliability of low-resource embeddings using corpus similarity measures that remain robust on small amounts of data. These findings have significant implications for the evaluation of truly low-resource languages in which such systematic downstream validation methods are not possible because of data limitations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dunn-etal-2022-predicting">
<titleInfo>
<title>Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Dunn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haipeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damian</namePart>
<namePart type="family">Sastre</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>This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible to estimate the reliability of low-resource embeddings using corpus similarity measures that remain robust on small amounts of data. These findings have significant implications for the evaluation of truly low-resource languages in which such systematic downstream validation methods are not possible because of data limitations.</abstract>
<identifier type="citekey">dunn-etal-2022-predicting</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.693</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6461</start>
<end>6470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures
%A Dunn, Jonathan
%A Li, Haipeng
%A Sastre, Damian
%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 dunn-etal-2022-predicting
%X This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible to estimate the reliability of low-resource embeddings using corpus similarity measures that remain robust on small amounts of data. These findings have significant implications for the evaluation of truly low-resource languages in which such systematic downstream validation methods are not possible because of data limitations.
%U https://aclanthology.org/2022.lrec-1.693
%P 6461-6470
Markdown (Informal)
[Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures](https://aclanthology.org/2022.lrec-1.693) (Dunn et al., LREC 2022)
ACL