@inproceedings{ivacic-etal-2023-analysis,
title = "Analysis of Transfer Learning for Named Entity Recognition in {S}outh-{S}lavic Languages",
author = "Iva{\v{c}}i{\v{c}}, Nikola and
Tran, Thi Hong Hanh and
Koloski, Boshko and
Pollak, Senja and
Purver, Matthew",
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-1.13",
doi = "10.18653/v1/2023.bsnlp-1.13",
pages = "106--112",
abstract = "This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the {``}low resource{''} languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ivacic-etal-2023-analysis">
<titleInfo>
<title>Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ivačič</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thi</namePart>
<namePart type="given">Hong</namePart>
<namePart type="given">Hanh</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boshko</namePart>
<namePart type="family">Koloski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</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>This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the “low resource” languages.</abstract>
<identifier type="citekey">ivacic-etal-2023-analysis</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.13</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.13</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>106</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages
%A Ivačič, Nikola
%A Tran, Thi Hong Hanh
%A Koloski, Boshko
%A Pollak, Senja
%A Purver, Matthew
%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 ivacic-etal-2023-analysis
%X This paper analyzes a Named Entity Recognition task for South-Slavic languages using the pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. We have shown that the model performance is not influenced substantially when trained with other than a target language. While for Slovene, the monolingual setting generally performs better, for Croatian and Serbian the results are slightly better in selected cross-lingual settings, but the improvements are not large. The most significant performance improvement is shown for the Serbian language, which has the smallest corpora. Therefore, fine-tuning with other closely related languages may benefit only the “low resource” languages.
%R 10.18653/v1/2023.bsnlp-1.13
%U https://aclanthology.org/2023.bsnlp-1.13
%U https://doi.org/10.18653/v1/2023.bsnlp-1.13
%P 106-112
Markdown (Informal)
[Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages](https://aclanthology.org/2023.bsnlp-1.13) (Ivačič et al., BSNLP 2023)
ACL