@inproceedings{suppa-jariabka-2021-benchmarking,
title = "Benchmarking Pre-trained Language Models for Multilingual {NER}: {T}ra{S}pa{S} at the {BSNLP}2021 Shared Task",
author = "Suppa, Marek and
Jariabka, Ondrej",
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-1.13",
pages = "105--114",
abstract = "In this paper we describe TraSpaS, a submission to the third shared task on named entity recognition hosted as part of the Balto-Slavic Natural Language Processing (BSNLP) Workshop. In it we evaluate various pre-trained language models on the NER task using three open-source NLP toolkits: character level language model with Stanza, language-specific BERT-style models with SpaCy and Adapter-enabled XLM-R with Trankit. Our results show that the Trankit-based models outperformed those based on the other two toolkits, even when trained on smaller amounts of data. Our code is available at \url{https://github.com/NaiveNeuron/slavner-2021}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suppa-jariabka-2021-benchmarking">
<titleInfo>
<title>Benchmarking Pre-trained Language Models for Multilingual NER: TraSpaS at the BSNLP2021 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Suppa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Jariabka</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>In this paper we describe TraSpaS, a submission to the third shared task on named entity recognition hosted as part of the Balto-Slavic Natural Language Processing (BSNLP) Workshop. In it we evaluate various pre-trained language models on the NER task using three open-source NLP toolkits: character level language model with Stanza, language-specific BERT-style models with SpaCy and Adapter-enabled XLM-R with Trankit. Our results show that the Trankit-based models outperformed those based on the other two toolkits, even when trained on smaller amounts of data. Our code is available at https://github.com/NaiveNeuron/slavner-2021.</abstract>
<identifier type="citekey">suppa-jariabka-2021-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2021.bsnlp-1.13</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>105</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Pre-trained Language Models for Multilingual NER: TraSpaS at the BSNLP2021 Shared Task
%A Suppa, Marek
%A Jariabka, Ondrej
%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 suppa-jariabka-2021-benchmarking
%X In this paper we describe TraSpaS, a submission to the third shared task on named entity recognition hosted as part of the Balto-Slavic Natural Language Processing (BSNLP) Workshop. In it we evaluate various pre-trained language models on the NER task using three open-source NLP toolkits: character level language model with Stanza, language-specific BERT-style models with SpaCy and Adapter-enabled XLM-R with Trankit. Our results show that the Trankit-based models outperformed those based on the other two toolkits, even when trained on smaller amounts of data. Our code is available at https://github.com/NaiveNeuron/slavner-2021.
%U https://aclanthology.org/2021.bsnlp-1.13
%P 105-114
Markdown (Informal)
[Benchmarking Pre-trained Language Models for Multilingual NER: TraSpaS at the BSNLP2021 Shared Task](https://aclanthology.org/2021.bsnlp-1.13) (Suppa & Jariabka, BSNLP 2021)
ACL