@inproceedings{shavrina-etal-2020-russiansuperglue,
title = "{R}ussian{S}uper{GLUE}: A {R}ussian Language Understanding Evaluation Benchmark",
author = "Shavrina, Tatiana and
Fenogenova, Alena and
Anton, Emelyanov and
Shevelev, Denis and
Artemova, Ekaterina and
Malykh, Valentin and
Mikhailov, Vladislav and
Tikhonova, Maria and
Chertok, Andrey and
Evlampiev, Andrey",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.381",
doi = "10.18653/v1/2020.emnlp-main.381",
pages = "4717--4726",
abstract = "In this paper, we introduce an advanced Russian general language understanding evaluation benchmark {--} Russian SuperGLUE. Recent advances in the field of universal language models and transformers require the development of a methodology for their broad diagnostics and testing for general intellectual skills - detection of natural language inference, commonsense reasoning, ability to perform simple logical operations regardless of text subject or lexicon. For the first time, a benchmark of nine tasks, collected and organized analogically to the SuperGLUE methodology, was developed from scratch for the Russian language. We also provide baselines, human level evaluation, open-source framework for evaluating models, and an overall leaderboard of transformer models for the Russian language. Besides, we present the first results of comparing multilingual models in the translated diagnostic test set and offer the first steps to further expanding or assessing State-of-the-art models independently of language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shavrina-etal-2020-russiansuperglue">
<titleInfo>
<title>RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alena</namePart>
<namePart type="family">Fenogenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emelyanov</namePart>
<namePart type="family">Anton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Shevelev</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>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Maria</namePart>
<namePart type="family">Tikhonova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Chertok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrey</namePart>
<namePart type="family">Evlampiev</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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>In this paper, we introduce an advanced Russian general language understanding evaluation benchmark – Russian SuperGLUE. Recent advances in the field of universal language models and transformers require the development of a methodology for their broad diagnostics and testing for general intellectual skills - detection of natural language inference, commonsense reasoning, ability to perform simple logical operations regardless of text subject or lexicon. For the first time, a benchmark of nine tasks, collected and organized analogically to the SuperGLUE methodology, was developed from scratch for the Russian language. We also provide baselines, human level evaluation, open-source framework for evaluating models, and an overall leaderboard of transformer models for the Russian language. Besides, we present the first results of comparing multilingual models in the translated diagnostic test set and offer the first steps to further expanding or assessing State-of-the-art models independently of language.</abstract>
<identifier type="citekey">shavrina-etal-2020-russiansuperglue</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.381</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.381</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4717</start>
<end>4726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
%A Shavrina, Tatiana
%A Fenogenova, Alena
%A Anton, Emelyanov
%A Shevelev, Denis
%A Artemova, Ekaterina
%A Malykh, Valentin
%A Mikhailov, Vladislav
%A Tikhonova, Maria
%A Chertok, Andrey
%A Evlampiev, Andrey
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F shavrina-etal-2020-russiansuperglue
%X In this paper, we introduce an advanced Russian general language understanding evaluation benchmark – Russian SuperGLUE. Recent advances in the field of universal language models and transformers require the development of a methodology for their broad diagnostics and testing for general intellectual skills - detection of natural language inference, commonsense reasoning, ability to perform simple logical operations regardless of text subject or lexicon. For the first time, a benchmark of nine tasks, collected and organized analogically to the SuperGLUE methodology, was developed from scratch for the Russian language. We also provide baselines, human level evaluation, open-source framework for evaluating models, and an overall leaderboard of transformer models for the Russian language. Besides, we present the first results of comparing multilingual models in the translated diagnostic test set and offer the first steps to further expanding or assessing State-of-the-art models independently of language.
%R 10.18653/v1/2020.emnlp-main.381
%U https://aclanthology.org/2020.emnlp-main.381
%U https://doi.org/10.18653/v1/2020.emnlp-main.381
%P 4717-4726
Markdown (Informal)
[RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark](https://aclanthology.org/2020.emnlp-main.381) (Shavrina et al., EMNLP 2020)
ACL
- Tatiana Shavrina, Alena Fenogenova, Emelyanov Anton, Denis Shevelev, Ekaterina Artemova, Valentin Malykh, Vladislav Mikhailov, Maria Tikhonova, Andrey Chertok, and Andrey Evlampiev. 2020. RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4717–4726, Online. Association for Computational Linguistics.