@inproceedings{mysiak-cyranka-2023-german,
title = "Is {G}erman secretly a {S}lavic language? What {BERT} probing can tell us about language groups",
author = "Mysiak, Aleksandra and
Cyranka, Jacek",
editor = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Ogrodniczuk, Maciej and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Rybak, Piotr and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bsnlp-1.11/",
doi = "10.18653/v1/2023.bsnlp-1.11",
pages = "86--93",
abstract = "In the light of recent developments in NLP, the problem of understanding and interpreting large language models has gained a lot of urgency. Methods developed to study this area are subject to considerable scrutiny. In this work, we take a closer look at one such method, the structural probe introduced by Hewitt and Manning (2019). We run a series of experiments involving multiple languages, focusing principally on the group of Slavic languages. We show that probing results can be seen as a reflection of linguistic classification, and conclude that multilingual BERT learns facts about languages and their groups."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mysiak-cyranka-2023-german">
<titleInfo>
<title>Is German secretly a Slavic language? What BERT probing can tell us about language groups</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Mysiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacek</namePart>
<namePart type="family">Cyranka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</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">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the light of recent developments in NLP, the problem of understanding and interpreting large language models has gained a lot of urgency. Methods developed to study this area are subject to considerable scrutiny. In this work, we take a closer look at one such method, the structural probe introduced by Hewitt and Manning (2019). We run a series of experiments involving multiple languages, focusing principally on the group of Slavic languages. We show that probing results can be seen as a reflection of linguistic classification, and conclude that multilingual BERT learns facts about languages and their groups.</abstract>
<identifier type="citekey">mysiak-cyranka-2023-german</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.11/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>86</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is German secretly a Slavic language? What BERT probing can tell us about language groups
%A Mysiak, Aleksandra
%A Cyranka, Jacek
%Y Piskorski, Jakub
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Ogrodniczuk, Maciej
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Rybak, Piotr
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F mysiak-cyranka-2023-german
%X In the light of recent developments in NLP, the problem of understanding and interpreting large language models has gained a lot of urgency. Methods developed to study this area are subject to considerable scrutiny. In this work, we take a closer look at one such method, the structural probe introduced by Hewitt and Manning (2019). We run a series of experiments involving multiple languages, focusing principally on the group of Slavic languages. We show that probing results can be seen as a reflection of linguistic classification, and conclude that multilingual BERT learns facts about languages and their groups.
%R 10.18653/v1/2023.bsnlp-1.11
%U https://aclanthology.org/2023.bsnlp-1.11/
%U https://doi.org/10.18653/v1/2023.bsnlp-1.11
%P 86-93
Markdown (Informal)
[Is German secretly a Slavic language? What BERT probing can tell us about language groups](https://aclanthology.org/2023.bsnlp-1.11/) (Mysiak & Cyranka, BSNLP 2023)
ACL