@inproceedings{li-etal-2021-improving-cross,
title = "Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting",
author = "Li, Irene and
Sen, Prithviraj and
Zhu, Huaiyu and
Li, Yunyao and
Radev, Dragomir",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.1",
doi = "10.18653/v1/2021.repl4nlp-1.1",
pages = "1--7",
abstract = "Cross-lingual text classification (CLTC) is a challenging task made even harder still due to the lack of labeled data in low-resource languages. In this paper, we propose zero-shot instance-weighting, a general model-agnostic zero-shot learning framework for improving CLTC by leveraging source instance weighting. It adds a module on top of pre-trained language models for similarity computation of instance weights, thus aligning each source instance to the target language. During training, the framework utilizes gradient descent that is weighted by instance weights to update parameters. We evaluate this framework over seven target languages on three fundamental tasks and show its effectiveness and extensibility, by improving on F1 score up to 4{\%} in single-source transfer and 8{\%} in multi-source transfer. To the best of our knowledge, our method is the first to apply instance weighting in zero-shot CLTC. It is simple yet effective and easily extensible into multi-source transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-improving-cross">
<titleInfo>
<title>Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prithviraj</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaiyu</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</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>Cross-lingual text classification (CLTC) is a challenging task made even harder still due to the lack of labeled data in low-resource languages. In this paper, we propose zero-shot instance-weighting, a general model-agnostic zero-shot learning framework for improving CLTC by leveraging source instance weighting. It adds a module on top of pre-trained language models for similarity computation of instance weights, thus aligning each source instance to the target language. During training, the framework utilizes gradient descent that is weighted by instance weights to update parameters. We evaluate this framework over seven target languages on three fundamental tasks and show its effectiveness and extensibility, by improving on F1 score up to 4% in single-source transfer and 8% in multi-source transfer. To the best of our knowledge, our method is the first to apply instance weighting in zero-shot CLTC. It is simple yet effective and easily extensible into multi-source transfer.</abstract>
<identifier type="citekey">li-etal-2021-improving-cross</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.1</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting
%A Li, Irene
%A Sen, Prithviraj
%A Zhu, Huaiyu
%A Li, Yunyao
%A Radev, Dragomir
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F li-etal-2021-improving-cross
%X Cross-lingual text classification (CLTC) is a challenging task made even harder still due to the lack of labeled data in low-resource languages. In this paper, we propose zero-shot instance-weighting, a general model-agnostic zero-shot learning framework for improving CLTC by leveraging source instance weighting. It adds a module on top of pre-trained language models for similarity computation of instance weights, thus aligning each source instance to the target language. During training, the framework utilizes gradient descent that is weighted by instance weights to update parameters. We evaluate this framework over seven target languages on three fundamental tasks and show its effectiveness and extensibility, by improving on F1 score up to 4% in single-source transfer and 8% in multi-source transfer. To the best of our knowledge, our method is the first to apply instance weighting in zero-shot CLTC. It is simple yet effective and easily extensible into multi-source transfer.
%R 10.18653/v1/2021.repl4nlp-1.1
%U https://aclanthology.org/2021.repl4nlp-1.1
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.1
%P 1-7
Markdown (Informal)
[Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting](https://aclanthology.org/2021.repl4nlp-1.1) (Li et al., RepL4NLP 2021)
ACL