<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-etal-2021-saliency-based">
    <titleInfo>
        <title>Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Siyu</namePart>
        <namePart type="family">Lai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dong</namePart>
        <namePart type="family">Jing</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yufeng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jian</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks. However, there are still gaps between the contextualized representations of similar words in different languages. To solve this problem, we propose a novel framework named Multi-View Mixed Language Training (MVMLT), which leverages code-switched data with multi-view learning to fine-tune XLM-R. MVMLT uses gradient-based saliency to extract keywords which are the most relevant to downstream tasks and replaces them with the corresponding words in the target language dynamically. Furthermore, MVMLT utilizes multi-view learning to encourage contextualized embeddings to align into a more refined language-invariant space. Extensive experiments with four languages show that our model achieves state-of-the-art results on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks, demonstrating the effectiveness of our proposed model.</abstract>
    <identifier type="citekey">lai-etal-2021-saliency-based</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.55</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.55</url>
    </location>
    <part>
        <date>2021-nov</date>
        <extent unit="page">
            <start>599</start>
            <end>610</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification
%A Lai, Siyu
%A Huang, Hui
%A Jing, Dong
%A Chen, Yufeng
%A Xu, Jinan
%A Liu, Jian
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F lai-etal-2021-saliency-based
%X Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks. However, there are still gaps between the contextualized representations of similar words in different languages. To solve this problem, we propose a novel framework named Multi-View Mixed Language Training (MVMLT), which leverages code-switched data with multi-view learning to fine-tune XLM-R. MVMLT uses gradient-based saliency to extract keywords which are the most relevant to downstream tasks and replaces them with the corresponding words in the target language dynamically. Furthermore, MVMLT utilizes multi-view learning to encourage contextualized embeddings to align into a more refined language-invariant space. Extensive experiments with four languages show that our model achieves state-of-the-art results on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks, demonstrating the effectiveness of our proposed model.
%R 10.18653/v1/2021.findings-emnlp.55
%U https://aclanthology.org/2021.findings-emnlp.55
%U https://doi.org/10.18653/v1/2021.findings-emnlp.55
%P 599-610

Markdown (Informal)

[Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification](https://aclanthology.org/2021.findings-emnlp.55) (Lai et al., Findings 2021)

• Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification (Lai et al., Findings 2021)

ACL

• Siyu Lai, Hui Huang, Dong Jing, Yufeng Chen, Jinan Xu, and Jian Liu. 2021. Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 599–610, Punta Cana, Dominican Republic. Association for Computational Linguistics.