@inproceedings{zhou-etal-2022-richer,
title = "Richer Countries and Richer Representations",
author = "Zhou, Kaitlyn and
Ethayarajh, Kawin and
Jurafsky, Dan",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.164",
doi = "10.18653/v1/2022.findings-acl.164",
pages = "2074--2085",
abstract = "We examine whether some countries are more richly represented in embedding space than others. We find that countries whose names occur with low frequency in training corpora are more likely to be tokenized into subwords, are less semantically distinct in embedding space, and are less likely to be correctly predicted: e.g., Ghana (the correct answer and in-vocabulary) is not predicted for, {``}The country producing the most cocoa is [MASK].{''}. Although these performance discrepancies and representational harms are due to frequency, we find that frequency is highly correlated with a country{'}s GDP; thus perpetuating historic power and wealth inequalities. We analyze the effectiveness of mitigation strategies; recommend that researchers report training word frequencies; and recommend future work for the community to define and design representational guarantees.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2022-richer">
<titleInfo>
<title>Richer Countries and Richer Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaitlyn</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kawin</namePart>
<namePart type="family">Ethayarajh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We examine whether some countries are more richly represented in embedding space than others. We find that countries whose names occur with low frequency in training corpora are more likely to be tokenized into subwords, are less semantically distinct in embedding space, and are less likely to be correctly predicted: e.g., Ghana (the correct answer and in-vocabulary) is not predicted for, “The country producing the most cocoa is [MASK].”. Although these performance discrepancies and representational harms are due to frequency, we find that frequency is highly correlated with a country’s GDP; thus perpetuating historic power and wealth inequalities. We analyze the effectiveness of mitigation strategies; recommend that researchers report training word frequencies; and recommend future work for the community to define and design representational guarantees.</abstract>
<identifier type="citekey">zhou-etal-2022-richer</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.164</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.164</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2074</start>
<end>2085</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Richer Countries and Richer Representations
%A Zhou, Kaitlyn
%A Ethayarajh, Kawin
%A Jurafsky, Dan
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F zhou-etal-2022-richer
%X We examine whether some countries are more richly represented in embedding space than others. We find that countries whose names occur with low frequency in training corpora are more likely to be tokenized into subwords, are less semantically distinct in embedding space, and are less likely to be correctly predicted: e.g., Ghana (the correct answer and in-vocabulary) is not predicted for, “The country producing the most cocoa is [MASK].”. Although these performance discrepancies and representational harms are due to frequency, we find that frequency is highly correlated with a country’s GDP; thus perpetuating historic power and wealth inequalities. We analyze the effectiveness of mitigation strategies; recommend that researchers report training word frequencies; and recommend future work for the community to define and design representational guarantees.
%R 10.18653/v1/2022.findings-acl.164
%U https://aclanthology.org/2022.findings-acl.164
%U https://doi.org/10.18653/v1/2022.findings-acl.164
%P 2074-2085
Markdown (Informal)
[Richer Countries and Richer Representations](https://aclanthology.org/2022.findings-acl.164) (Zhou et al., Findings 2022)
ACL
- Kaitlyn Zhou, Kawin Ethayarajh, and Dan Jurafsky. 2022. Richer Countries and Richer Representations. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2074–2085, Dublin, Ireland. Association for Computational Linguistics.