<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maurya-desarkar-2022-meta">
    <titleInfo>
        <title>Meta-X_NLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kaushal</namePart>
        <namePart type="family">Maurya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maunendra</namePart>
        <namePart type="family">Desarkar</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>Findings of the Association for Computational Linguistics: ACL 2022</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>Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the cross-lingual transfer is not uniform across languages, particularly in the zero-shot setting. Towards this goal, one promising research direction is to learn shareable structures across multiple tasks with limited annotated data. The downstream multilingual applications may benefit from such a learning setup as most of the languages across the globe are low-resource and share some structures with other languages. In this paper, we propose a novel meta-learning framework (called Meta-X_NLG) to learn shareable structures from typologically diverse languages based on meta-learning and language clustering. This is a step towards uniform cross-lingual transfer for unseen languages. We first cluster the languages based on language representations and identify the centroid language of each cluster. Then, a meta-learning algorithm is trained with all centroid languages and evaluated on the other languages in the zero-shot setting. We demonstrate the effectiveness of this modeling on two NLG tasks (Abstractive Text Summarization and Question Generation), 5 popular datasets and 30 typologically diverse languages. Consistent improvements over strong baselines demonstrate the efficacy of the proposed framework. The careful design of the model makes this end-to-end NLG setup less vulnerable to the accidental translation problem, which is a prominent concern in zero-shot cross-lingual NLG tasks.</abstract>
    <identifier type="citekey">maurya-desarkar-2022-meta</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.24</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.24</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>269</start>
            <end>284</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Meta-X_NLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation
%A Maurya, Kaushal
%A Desarkar, Maunendra
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F maurya-desarkar-2022-meta
%X Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the cross-lingual transfer is not uniform across languages, particularly in the zero-shot setting. Towards this goal, one promising research direction is to learn shareable structures across multiple tasks with limited annotated data. The downstream multilingual applications may benefit from such a learning setup as most of the languages across the globe are low-resource and share some structures with other languages. In this paper, we propose a novel meta-learning framework (called Meta-X_NLG) to learn shareable structures from typologically diverse languages based on meta-learning and language clustering. This is a step towards uniform cross-lingual transfer for unseen languages. We first cluster the languages based on language representations and identify the centroid language of each cluster. Then, a meta-learning algorithm is trained with all centroid languages and evaluated on the other languages in the zero-shot setting. We demonstrate the effectiveness of this modeling on two NLG tasks (Abstractive Text Summarization and Question Generation), 5 popular datasets and 30 typologically diverse languages. Consistent improvements over strong baselines demonstrate the efficacy of the proposed framework. The careful design of the model makes this end-to-end NLG setup less vulnerable to the accidental translation problem, which is a prominent concern in zero-shot cross-lingual NLG tasks.
%R 10.18653/v1/2022.findings-acl.24
%U https://aclanthology.org/2022.findings-acl.24
%U https://doi.org/10.18653/v1/2022.findings-acl.24
%P 269-284

Markdown (Informal)

[Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation](https://aclanthology.org/2022.findings-acl.24) (Maurya & Desarkar, Findings 2022)

• Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation (Maurya & Desarkar, Findings 2022)

ACL

• Kaushal Maurya and Maunendra Desarkar. 2022. Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 269–284, Dublin, Ireland. Association for Computational Linguistics.