@inproceedings{otmakhova-etal-2022-cross,
title = "Cross-linguistic Comparison of Linguistic Feature Encoding in {BERT} Models for Typologically Different Languages",
author = "Otmakhova, Yulia and
Verspoor, Karin and
Lau, Jey Han",
editor = "Vylomova, Ekaterina and
Ponti, Edoardo and
Cotterell, Ryan",
booktitle = "Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigtyp-1.4/",
doi = "10.18653/v1/2022.sigtyp-1.4",
pages = "27--35",
abstract = "Though recently there have been an increased interest in how pre-trained language models encode different linguistic features, there is still a lack of systematic comparison between languages with different morphology and syntax. In this paper, using BERT as an example of a pre-trained model, we compare how three typologically different languages (English, Korean, and Russian) encode morphology and syntax features across different layers. In particular, we contrast languages which differ in a particular aspect, such as flexibility of word order, head directionality, morphological type, presence of grammatical gender, and morphological richness, across four different tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otmakhova-etal-2022-cross">
<titleInfo>
<title>Cross-linguistic Comparison of Linguistic Feature Encoding in BERT Models for Typologically Different Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Otmakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jey</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Though recently there have been an increased interest in how pre-trained language models encode different linguistic features, there is still a lack of systematic comparison between languages with different morphology and syntax. In this paper, using BERT as an example of a pre-trained model, we compare how three typologically different languages (English, Korean, and Russian) encode morphology and syntax features across different layers. In particular, we contrast languages which differ in a particular aspect, such as flexibility of word order, head directionality, morphological type, presence of grammatical gender, and morphological richness, across four different tasks.</abstract>
<identifier type="citekey">otmakhova-etal-2022-cross</identifier>
<identifier type="doi">10.18653/v1/2022.sigtyp-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.sigtyp-1.4/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>27</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-linguistic Comparison of Linguistic Feature Encoding in BERT Models for Typologically Different Languages
%A Otmakhova, Yulia
%A Verspoor, Karin
%A Lau, Jey Han
%Y Vylomova, Ekaterina
%Y Ponti, Edoardo
%Y Cotterell, Ryan
%S Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F otmakhova-etal-2022-cross
%X Though recently there have been an increased interest in how pre-trained language models encode different linguistic features, there is still a lack of systematic comparison between languages with different morphology and syntax. In this paper, using BERT as an example of a pre-trained model, we compare how three typologically different languages (English, Korean, and Russian) encode morphology and syntax features across different layers. In particular, we contrast languages which differ in a particular aspect, such as flexibility of word order, head directionality, morphological type, presence of grammatical gender, and morphological richness, across four different tasks.
%R 10.18653/v1/2022.sigtyp-1.4
%U https://aclanthology.org/2022.sigtyp-1.4/
%U https://doi.org/10.18653/v1/2022.sigtyp-1.4
%P 27-35
Markdown (Informal)
[Cross-linguistic Comparison of Linguistic Feature Encoding in BERT Models for Typologically Different Languages](https://aclanthology.org/2022.sigtyp-1.4/) (Otmakhova et al., SIGTYP 2022)
ACL