@inproceedings{de-vries-etal-2022-make,
title = "Make the Best of Cross-lingual Transfer: Evidence from {POS} Tagging with over 100 Languages",
author = "de Vries, Wietse and
Wieling, Martijn and
Nissim, Malvina",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.529/",
doi = "10.18653/v1/2022.acl-long.529",
pages = "7676--7685",
abstract = "Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data. Existing evaluations of zero-shot cross-lingual generalisability of large pre-trained models use datasets with English training data, and test data in a selection of target languages. We explore a more extensive transfer learning setup with 65 different source languages and 105 target languages for part-of-speech tagging. Through our analysis, we show that pre-training of both source and target language, as well as matching language families, writing systems, word order systems, and lexical-phonetic distance significantly impact cross-lingual performance. The findings described in this paper can be used as indicators of which factors are important for effective zero-shot cross-lingual transfer to zero- and low-resource languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-vries-etal-2022-make">
<titleInfo>
<title>Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wietse</namePart>
<namePart type="family">de Vries</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Wieling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</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">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data. Existing evaluations of zero-shot cross-lingual generalisability of large pre-trained models use datasets with English training data, and test data in a selection of target languages. We explore a more extensive transfer learning setup with 65 different source languages and 105 target languages for part-of-speech tagging. Through our analysis, we show that pre-training of both source and target language, as well as matching language families, writing systems, word order systems, and lexical-phonetic distance significantly impact cross-lingual performance. The findings described in this paper can be used as indicators of which factors are important for effective zero-shot cross-lingual transfer to zero- and low-resource languages.</abstract>
<identifier type="citekey">de-vries-etal-2022-make</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.529</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.529/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>7676</start>
<end>7685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages
%A de Vries, Wietse
%A Wieling, Martijn
%A Nissim, Malvina
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F de-vries-etal-2022-make
%X Cross-lingual transfer learning with large multilingual pre-trained models can be an effective approach for low-resource languages with no labeled training data. Existing evaluations of zero-shot cross-lingual generalisability of large pre-trained models use datasets with English training data, and test data in a selection of target languages. We explore a more extensive transfer learning setup with 65 different source languages and 105 target languages for part-of-speech tagging. Through our analysis, we show that pre-training of both source and target language, as well as matching language families, writing systems, word order systems, and lexical-phonetic distance significantly impact cross-lingual performance. The findings described in this paper can be used as indicators of which factors are important for effective zero-shot cross-lingual transfer to zero- and low-resource languages.
%R 10.18653/v1/2022.acl-long.529
%U https://aclanthology.org/2022.acl-long.529/
%U https://doi.org/10.18653/v1/2022.acl-long.529
%P 7676-7685
Markdown (Informal)
[Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages](https://aclanthology.org/2022.acl-long.529/) (de Vries et al., ACL 2022)
ACL