@inproceedings{deb-etal-2023-zero,
title = "Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data",
author = "Deb, Ujan and
Parab, Ridayesh and
Jyothi, Preethi",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.39",
doi = "10.18653/v1/2023.acl-short.39",
pages = "449--457",
abstract = "Adapters have emerged as a parameter-efficient Transformer-based framework for cross-lingual transfer by inserting lightweight language-specific modules (language adapters) and task-specific modules (task adapters) within pretrained multilingual models. Zero-shot transfer is enabled by pairing the language adapter in the target language with an appropriate task adapter in a source language. If our target languages are known apriori, we explore how zero-shot transfer can be further improved within the adapter framework by utilizing unlabeled text during task-specific finetuning. We construct language-specific subspaces using standard linear algebra constructs and selectively project source-language representations into the target language subspace during task-specific finetuning using two schemes. Our experiments on three cross-lingual tasks, Named Entity Recognition (NER), Question Answering (QA) and Natural Language Inference (NLI) yield consistent benefits compared to adapter baselines over a wide variety of target languages with up to 11{\%} relative improvement in NER, 2{\%} relative improvement in QA and 5{\%} relative improvement in NLI.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deb-etal-2023-zero">
<titleInfo>
<title>Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ujan</namePart>
<namePart type="family">Deb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ridayesh</namePart>
<namePart type="family">Parab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adapters have emerged as a parameter-efficient Transformer-based framework for cross-lingual transfer by inserting lightweight language-specific modules (language adapters) and task-specific modules (task adapters) within pretrained multilingual models. Zero-shot transfer is enabled by pairing the language adapter in the target language with an appropriate task adapter in a source language. If our target languages are known apriori, we explore how zero-shot transfer can be further improved within the adapter framework by utilizing unlabeled text during task-specific finetuning. We construct language-specific subspaces using standard linear algebra constructs and selectively project source-language representations into the target language subspace during task-specific finetuning using two schemes. Our experiments on three cross-lingual tasks, Named Entity Recognition (NER), Question Answering (QA) and Natural Language Inference (NLI) yield consistent benefits compared to adapter baselines over a wide variety of target languages with up to 11% relative improvement in NER, 2% relative improvement in QA and 5% relative improvement in NLI.</abstract>
<identifier type="citekey">deb-etal-2023-zero</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.39</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.39</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>449</start>
<end>457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data
%A Deb, Ujan
%A Parab, Ridayesh
%A Jyothi, Preethi
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F deb-etal-2023-zero
%X Adapters have emerged as a parameter-efficient Transformer-based framework for cross-lingual transfer by inserting lightweight language-specific modules (language adapters) and task-specific modules (task adapters) within pretrained multilingual models. Zero-shot transfer is enabled by pairing the language adapter in the target language with an appropriate task adapter in a source language. If our target languages are known apriori, we explore how zero-shot transfer can be further improved within the adapter framework by utilizing unlabeled text during task-specific finetuning. We construct language-specific subspaces using standard linear algebra constructs and selectively project source-language representations into the target language subspace during task-specific finetuning using two schemes. Our experiments on three cross-lingual tasks, Named Entity Recognition (NER), Question Answering (QA) and Natural Language Inference (NLI) yield consistent benefits compared to adapter baselines over a wide variety of target languages with up to 11% relative improvement in NER, 2% relative improvement in QA and 5% relative improvement in NLI.
%R 10.18653/v1/2023.acl-short.39
%U https://aclanthology.org/2023.acl-short.39
%U https://doi.org/10.18653/v1/2023.acl-short.39
%P 449-457
Markdown (Informal)
[Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data](https://aclanthology.org/2023.acl-short.39) (Deb et al., ACL 2023)
ACL