@inproceedings{mikhailov-etal-2021-rusenteval,
title = "{R}u{S}ent{E}val: Linguistic Source, Encoder Force!",
author = "Mikhailov, Vladislav and
Taktasheva, Ekaterina and
Sigdel, Elina and
Artemova, Ekaterina",
editor = "Babych, Bogdan and
Kanishcheva, Olga and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
Starko, Vasyl and
Steinberger, Josef and
Yangarber, Roman and
Marci{\'n}czuk, Micha{\l} and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Robnik-{\v{S}}ikonja, Marko",
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bsnlp-1.6/",
pages = "43--65",
abstract = "The success of pre-trained transformer language models has brought a great deal of interest on how these models work, and what they learn about language. However, prior research in the field is mainly devoted to English, and little is known regarding other languages. To this end, we introduce RuSentEval, an enhanced set of 14 probing tasks for Russian, including ones that have not been explored yet. We apply a combination of complementary probing methods to explore the distribution of various linguistic properties in five multilingual transformers for two typologically contrasting languages {--} Russian and English. Our results provide intriguing findings that contradict the common understanding of how linguistic knowledge is represented, and demonstrate that some properties are learned in a similar manner despite the language differences."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mikhailov-etal-2021-rusenteval">
<titleInfo>
<title>RuSentEval: Linguistic Source, Encoder Force!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Taktasheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elina</namePart>
<namePart type="family">Sigdel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bogdan</namePart>
<namePart type="family">Babych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kanishcheva</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">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasyl</namePart>
<namePart type="family">Starko</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>
<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">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">Marko</namePart>
<namePart type="family">Robnik-Šikonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The success of pre-trained transformer language models has brought a great deal of interest on how these models work, and what they learn about language. However, prior research in the field is mainly devoted to English, and little is known regarding other languages. To this end, we introduce RuSentEval, an enhanced set of 14 probing tasks for Russian, including ones that have not been explored yet. We apply a combination of complementary probing methods to explore the distribution of various linguistic properties in five multilingual transformers for two typologically contrasting languages – Russian and English. Our results provide intriguing findings that contradict the common understanding of how linguistic knowledge is represented, and demonstrate that some properties are learned in a similar manner despite the language differences.</abstract>
<identifier type="citekey">mikhailov-etal-2021-rusenteval</identifier>
<location>
<url>https://aclanthology.org/2021.bsnlp-1.6/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>43</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RuSentEval: Linguistic Source, Encoder Force!
%A Mikhailov, Vladislav
%A Taktasheva, Ekaterina
%A Sigdel, Elina
%A Artemova, Ekaterina
%Y Babych, Bogdan
%Y Kanishcheva, Olga
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Starko, Vasyl
%Y Steinberger, Josef
%Y Yangarber, Roman
%Y Marcińczuk, Michał
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Robnik-Šikonja, Marko
%S Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F mikhailov-etal-2021-rusenteval
%X The success of pre-trained transformer language models has brought a great deal of interest on how these models work, and what they learn about language. However, prior research in the field is mainly devoted to English, and little is known regarding other languages. To this end, we introduce RuSentEval, an enhanced set of 14 probing tasks for Russian, including ones that have not been explored yet. We apply a combination of complementary probing methods to explore the distribution of various linguistic properties in five multilingual transformers for two typologically contrasting languages – Russian and English. Our results provide intriguing findings that contradict the common understanding of how linguistic knowledge is represented, and demonstrate that some properties are learned in a similar manner despite the language differences.
%U https://aclanthology.org/2021.bsnlp-1.6/
%P 43-65
Markdown (Informal)
[RuSentEval: Linguistic Source, Encoder Force!](https://aclanthology.org/2021.bsnlp-1.6/) (Mikhailov et al., BSNLP 2021)
ACL
- Vladislav Mikhailov, Ekaterina Taktasheva, Elina Sigdel, and Ekaterina Artemova. 2021. RuSentEval: Linguistic Source, Encoder Force!. In Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing, pages 43–65, Kiyv, Ukraine. Association for Computational Linguistics.