<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ai-fang-2023-fly">
    <titleInfo>
        <title>On-the-fly Cross-lingual Masking for Multilingual Pre-training</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long 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>In multilingual pre-training with the objective of MLM (masked language modeling) on multiple monolingual corpora, multilingual models only learn cross-linguality implicitly from isomorphic spaces formed by overlapping different language spaces due to the lack of explicit cross-lingual forward pass. In this work, we present CLPM (Cross-lingual Prototype Masking), a dynamic and token-wise masking scheme, for multilingual pre-training, using a special token [\mathcalC]_x to replace a random token x in the input sentence. [\mathcalC]_x is a cross-lingual prototype for x and then forms an explicit cross-lingual forward pass. We instantiate CLPM for the multilingual pre-training phase of UNMT (unsupervised neural machine translation), and experiments show that CLPM can consistently improve the performance of UNMT models on {De, Ro, Ne } łeftrightarrow En. Beyond UNMT or bilingual tasks, we show that CLPM can consistently improve the performance of multilingual models on cross-lingual classification.</abstract>
    <identifier type="citekey">ai-fang-2023-fly</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.49</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.49</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>855</start>
            <end>876</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On-the-fly Cross-lingual Masking for Multilingual Pre-training
%A Ai, Xi
%A Fang, Bin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ai-fang-2023-fly
%X In multilingual pre-training with the objective of MLM (masked language modeling) on multiple monolingual corpora, multilingual models only learn cross-linguality implicitly from isomorphic spaces formed by overlapping different language spaces due to the lack of explicit cross-lingual forward pass. In this work, we present CLPM (Cross-lingual Prototype Masking), a dynamic and token-wise masking scheme, for multilingual pre-training, using a special token [\mathcalC]_x to replace a random token x in the input sentence. [\mathcalC]_x is a cross-lingual prototype for x and then forms an explicit cross-lingual forward pass. We instantiate CLPM for the multilingual pre-training phase of UNMT (unsupervised neural machine translation), and experiments show that CLPM can consistently improve the performance of UNMT models on {De, Ro, Ne } łeftrightarrow En. Beyond UNMT or bilingual tasks, we show that CLPM can consistently improve the performance of multilingual models on cross-lingual classification.
%R 10.18653/v1/2023.acl-long.49
%U https://aclanthology.org/2023.acl-long.49
%U https://doi.org/10.18653/v1/2023.acl-long.49
%P 855-876

Markdown (Informal)

[On-the-fly Cross-lingual Masking for Multilingual Pre-training](https://aclanthology.org/2023.acl-long.49) (Ai & Fang, ACL 2023)

• On-the-fly Cross-lingual Masking for Multilingual Pre-training (Ai & Fang, ACL 2023)

ACL

• Xi Ai and Bin Fang. 2023. On-the-fly Cross-lingual Masking for Multilingual Pre-training. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 855–876, Toronto, Canada. Association for Computational Linguistics.