@inproceedings{van-der-heijden-etal-2021-multilingual,
title = "Multilingual and cross-lingual document classification: A meta-learning approach",
author = "van der Heijden, Niels and
Yannakoudakis, Helen and
Mishra, Pushkar and
Shutova, Ekaterina",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.168",
doi = "10.18653/v1/2021.eacl-main.168",
pages = "1966--1976",
abstract = "The great majority of languages in the world are considered under-resourced for successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in low-resource languages and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint-training when limited target-language data is available during trai-ing. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability, and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state-of-the-art on a number of languages while performing on-par on others, using only a small amount of labeled data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-der-heijden-etal-2021-multilingual">
<titleInfo>
<title>Multilingual and cross-lingual document classification: A meta-learning approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niels</namePart>
<namePart type="family">van der Heijden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</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 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>The great majority of languages in the world are considered under-resourced for successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in low-resource languages and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint-training when limited target-language data is available during trai-ing. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability, and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state-of-the-art on a number of languages while performing on-par on others, using only a small amount of labeled data.</abstract>
<identifier type="citekey">van-der-heijden-etal-2021-multilingual</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.168</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.168</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1966</start>
<end>1976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual and cross-lingual document classification: A meta-learning approach
%A van der Heijden, Niels
%A Yannakoudakis, Helen
%A Mishra, Pushkar
%A Shutova, Ekaterina
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F van-der-heijden-etal-2021-multilingual
%X The great majority of languages in the world are considered under-resourced for successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in low-resource languages and demonstrate its effectiveness in two different settings: few-shot, cross-lingual adaptation to previously unseen languages; and multilingual joint-training when limited target-language data is available during trai-ing. We conduct a systematic comparison of several meta-learning methods, investigate multiple settings in terms of data availability, and show that meta-learning thrives in settings with a heterogeneous task distribution. We propose a simple, yet effective adjustment to existing meta-learning methods which allows for better and more stable learning, and set a new state-of-the-art on a number of languages while performing on-par on others, using only a small amount of labeled data.
%R 10.18653/v1/2021.eacl-main.168
%U https://aclanthology.org/2021.eacl-main.168
%U https://doi.org/10.18653/v1/2021.eacl-main.168
%P 1966-1976
Markdown (Informal)
[Multilingual and cross-lingual document classification: A meta-learning approach](https://aclanthology.org/2021.eacl-main.168) (van der Heijden et al., EACL 2021)
ACL