<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ai-fang-2023-multilingual">
    <titleInfo>
        <title>Multilingual Pre-training with Self-supervision from Global Co-occurrence Information</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xi</namePart>
        <namePart type="family">Ai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Fang</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Global co-occurrence information is the primary source of structural information on multilingual corpora, and we find that analogical/parallel compound words across languages have similar co-occurrence counts/frequencies (normalized) giving weak but stable self-supervision for cross-lingual transfer. Following the observation, we aim at associating contextualized representations with relevant (contextualized) representations across languages with the help of co-occurrence counts. The result is MLM-GC (MLM with Global Co-occurrence) pre-training that the model learns local bidirectional information from MLM and global co-occurrence information from a log-bilinear regression. Experiments show that MLM-GC pre-training substantially outperforms MLM pre-training for 4 downstream cross-lingual tasks and 1 additional monolingual task, showing the advantages of forming isomorphic spaces across languages.</abstract>
    <identifier type="citekey">ai-fang-2023-multilingual</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.475</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.475</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>7526</start>
            <end>7543</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual Pre-training with Self-supervision from Global Co-occurrence Information
%A Ai, Xi
%A Fang, Bin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ai-fang-2023-multilingual
%X Global co-occurrence information is the primary source of structural information on multilingual corpora, and we find that analogical/parallel compound words across languages have similar co-occurrence counts/frequencies (normalized) giving weak but stable self-supervision for cross-lingual transfer. Following the observation, we aim at associating contextualized representations with relevant (contextualized) representations across languages with the help of co-occurrence counts. The result is MLM-GC (MLM with Global Co-occurrence) pre-training that the model learns local bidirectional information from MLM and global co-occurrence information from a log-bilinear regression. Experiments show that MLM-GC pre-training substantially outperforms MLM pre-training for 4 downstream cross-lingual tasks and 1 additional monolingual task, showing the advantages of forming isomorphic spaces across languages.
%R 10.18653/v1/2023.findings-acl.475
%U https://aclanthology.org/2023.findings-acl.475
%U https://doi.org/10.18653/v1/2023.findings-acl.475
%P 7526-7543

Markdown (Informal)

[Multilingual Pre-training with Self-supervision from Global Co-occurrence Information](https://aclanthology.org/2023.findings-acl.475) (Ai & Fang, Findings 2023)

• Multilingual Pre-training with Self-supervision from Global Co-occurrence Information (Ai & Fang, Findings 2023)

ACL

• Xi Ai and Bin Fang. 2023. Multilingual Pre-training with Self-supervision from Global Co-occurrence Information. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7526–7543, Toronto, Canada. Association for Computational Linguistics.