@inproceedings{veeman-etal-2020-cross,
title = "Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment",
author = "Veeman, Hartger and
Allassonni{\`e}re-Tang, Marc and
Berdicevskis, Aleksandrs and
Basirat, Ali",
editor = "Fern{\'a}ndez, Raquel and
Linzen, Tal",
booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.conll-1.20",
doi = "10.18653/v1/2020.conll-1.20",
pages = "265--275",
abstract = "Grammatical gender is assigned to nouns differently in different languages. Are all factors that influence gender assignment idiosyncratic to languages or are there any that are universal? Using cross-lingual aligned word embeddings, we perform two experiments to address these questions about language typology and human cognition. In both experiments, we predict the gender of nouns in language X using a classifier trained on the nouns of language Y, and take the classifier{'}s accuracy as a measure of transferability of gender systems. First, we show that for 22 Indo-European languages the transferability decreases as the phylogenetic distance increases. This correlation supports the claim that some gender assignment factors are idiosyncratic, and as the languages diverge, the proportion of shared inherited idiosyncrasies diminishes. Second, we show that when the classifier is trained on two Afro-Asiatic languages and tested on the same 22 Indo-European languages (or vice versa), its performance is still significantly above the chance baseline, thus showing that universal factors exist and, moreover, can be captured by word embeddings. When the classifier is tested across families and on inanimate nouns only, the performance is still above baseline, indicating that the universal factors are not limited to biological sex.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="veeman-etal-2020-cross">
<titleInfo>
<title>Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hartger</namePart>
<namePart type="family">Veeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Allassonnière-Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandrs</namePart>
<namePart type="family">Berdicevskis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Basirat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical gender is assigned to nouns differently in different languages. Are all factors that influence gender assignment idiosyncratic to languages or are there any that are universal? Using cross-lingual aligned word embeddings, we perform two experiments to address these questions about language typology and human cognition. In both experiments, we predict the gender of nouns in language X using a classifier trained on the nouns of language Y, and take the classifier’s accuracy as a measure of transferability of gender systems. First, we show that for 22 Indo-European languages the transferability decreases as the phylogenetic distance increases. This correlation supports the claim that some gender assignment factors are idiosyncratic, and as the languages diverge, the proportion of shared inherited idiosyncrasies diminishes. Second, we show that when the classifier is trained on two Afro-Asiatic languages and tested on the same 22 Indo-European languages (or vice versa), its performance is still significantly above the chance baseline, thus showing that universal factors exist and, moreover, can be captured by word embeddings. When the classifier is tested across families and on inanimate nouns only, the performance is still above baseline, indicating that the universal factors are not limited to biological sex.</abstract>
<identifier type="citekey">veeman-etal-2020-cross</identifier>
<identifier type="doi">10.18653/v1/2020.conll-1.20</identifier>
<location>
<url>https://aclanthology.org/2020.conll-1.20</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>265</start>
<end>275</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment
%A Veeman, Hartger
%A Allassonnière-Tang, Marc
%A Berdicevskis, Aleksandrs
%A Basirat, Ali
%Y Fernández, Raquel
%Y Linzen, Tal
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F veeman-etal-2020-cross
%X Grammatical gender is assigned to nouns differently in different languages. Are all factors that influence gender assignment idiosyncratic to languages or are there any that are universal? Using cross-lingual aligned word embeddings, we perform two experiments to address these questions about language typology and human cognition. In both experiments, we predict the gender of nouns in language X using a classifier trained on the nouns of language Y, and take the classifier’s accuracy as a measure of transferability of gender systems. First, we show that for 22 Indo-European languages the transferability decreases as the phylogenetic distance increases. This correlation supports the claim that some gender assignment factors are idiosyncratic, and as the languages diverge, the proportion of shared inherited idiosyncrasies diminishes. Second, we show that when the classifier is trained on two Afro-Asiatic languages and tested on the same 22 Indo-European languages (or vice versa), its performance is still significantly above the chance baseline, thus showing that universal factors exist and, moreover, can be captured by word embeddings. When the classifier is tested across families and on inanimate nouns only, the performance is still above baseline, indicating that the universal factors are not limited to biological sex.
%R 10.18653/v1/2020.conll-1.20
%U https://aclanthology.org/2020.conll-1.20
%U https://doi.org/10.18653/v1/2020.conll-1.20
%P 265-275
Markdown (Informal)
[Cross-lingual Embeddings Reveal Universal and Lineage-Specific Patterns in Grammatical Gender Assignment](https://aclanthology.org/2020.conll-1.20) (Veeman et al., CoNLL 2020)
ACL