@inproceedings{gudnason-loftsson-2022-pre,
title = "Pre-training and Evaluating Transformer-based Language Models for {I}celandic",
author = "Da{\dh}ason, J{\'o}n Fri{\dh}rik and
Loftsson, Hrafn",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.804",
pages = "7386--7391",
abstract = "In this paper, we evaluate several Transformer-based language models for Icelandic on four downstream tasks: Part-of-Speech tagging, Named Entity Recognition. Dependency Parsing, and Automatic Text Summarization. We pre-train four types of monolingual ELECTRA and ConvBERT models and compare our results to a previously trained monolingual RoBERTa model and the multilingual mBERT model. We find that the Transformer models obtain better results, often by a large margin, compared to previous state-of-the-art models. Furthermore, our results indicate that pre-training larger language models results in a significant reduction in error rates in comparison to smaller models. Finally, our results show that the monolingual models for Icelandic outperform a comparably sized multilingual model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gudnason-loftsson-2022-pre">
<titleInfo>
<title>Pre-training and Evaluating Transformer-based Language Models for Icelandic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="given">Fri\dhrik</namePart>
<namePart type="family">Da\dhason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we evaluate several Transformer-based language models for Icelandic on four downstream tasks: Part-of-Speech tagging, Named Entity Recognition. Dependency Parsing, and Automatic Text Summarization. We pre-train four types of monolingual ELECTRA and ConvBERT models and compare our results to a previously trained monolingual RoBERTa model and the multilingual mBERT model. We find that the Transformer models obtain better results, often by a large margin, compared to previous state-of-the-art models. Furthermore, our results indicate that pre-training larger language models results in a significant reduction in error rates in comparison to smaller models. Finally, our results show that the monolingual models for Icelandic outperform a comparably sized multilingual model.</abstract>
<identifier type="citekey">gudnason-loftsson-2022-pre</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.804</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7386</start>
<end>7391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-training and Evaluating Transformer-based Language Models for Icelandic
%A Da\dhason, Jón Fri\dhrik
%A Loftsson, Hrafn
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F gudnason-loftsson-2022-pre
%X In this paper, we evaluate several Transformer-based language models for Icelandic on four downstream tasks: Part-of-Speech tagging, Named Entity Recognition. Dependency Parsing, and Automatic Text Summarization. We pre-train four types of monolingual ELECTRA and ConvBERT models and compare our results to a previously trained monolingual RoBERTa model and the multilingual mBERT model. We find that the Transformer models obtain better results, often by a large margin, compared to previous state-of-the-art models. Furthermore, our results indicate that pre-training larger language models results in a significant reduction in error rates in comparison to smaller models. Finally, our results show that the monolingual models for Icelandic outperform a comparably sized multilingual model.
%U https://aclanthology.org/2022.lrec-1.804
%P 7386-7391
Markdown (Informal)
[Pre-training and Evaluating Transformer-based Language Models for Icelandic](https://aclanthology.org/2022.lrec-1.804) (Daðason & Loftsson, LREC 2022)
ACL