@inproceedings{chen-etal-2023-xsim,
title = "x{SIM}++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages",
author = "Chen, Mingda and
Heffernan, Kevin and
{\c{C}}elebi, Onur and
Mourachko, Alexandre and
Schwenk, Holger",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.10",
doi = "10.18653/v1/2023.acl-short.10",
pages = "101--109",
abstract = "We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xsim, we show that xsim++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xsim++ also reports performance for different error types, offering more fine-grained feedbacks for model development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-xsim">
<titleInfo>
<title>xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingda</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Heffernan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Çelebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Mourachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holger</namePart>
<namePart type="family">Schwenk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xsim, we show that xsim++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xsim++ also reports performance for different error types, offering more fine-grained feedbacks for model development.</abstract>
<identifier type="citekey">chen-etal-2023-xsim</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.10</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.10</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>101</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages
%A Chen, Mingda
%A Heffernan, Kevin
%A Çelebi, Onur
%A Mourachko, Alexandre
%A Schwenk, Holger
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-xsim
%X We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xsim++. In comparison to xsim, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xsim, we show that xsim++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xsim++ also reports performance for different error types, offering more fine-grained feedbacks for model development.
%R 10.18653/v1/2023.acl-short.10
%U https://aclanthology.org/2023.acl-short.10
%U https://doi.org/10.18653/v1/2023.acl-short.10
%P 101-109
Markdown (Informal)
[xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages](https://aclanthology.org/2023.acl-short.10) (Chen et al., ACL 2023)
ACL