<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurfali-ostling-2021-probing">
    <titleInfo>
        <title>Probing Multilingual Language Models for Discourse</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Murathan</namePart>
        <namePart type="family">Kurfalı</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Robert</namePart>
        <namePart type="family">Östling</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Pre-trained multilingual language models have become an important building block in multilingual Natural Language Processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level knowledge across languages. This is done with a systematic evaluation on a broader set of discourse-level tasks than has been previously been assembled. We find that the XLM-RoBERTa family of models consistently show the best performance, by simultaneously being good monolingual models and degrading relatively little in a zero-shot setting. Our results also indicate that model distillation may hurt the ability of cross-lingual transfer of sentence representations, while language dissimilarity at most has a modest effect. We hope that our test suite, covering 5 tasks with a total of 22 languages in 10 distinct families, will serve as a useful evaluation platform for multilingual performance at and beyond the sentence level.</abstract>
    <identifier type="citekey">kurfali-ostling-2021-probing</identifier>
    <identifier type="doi">10.18653/v1/2021.repl4nlp-1.2</identifier>
    <location>
        <url>https://aclanthology.org/2021.repl4nlp-1.2</url>
    </location>
    <part>
        <date>2021-08</date>
        <extent unit="page">
            <start>8</start>
            <end>19</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Probing Multilingual Language Models for Discourse
%A Kurfalı, Murathan
%A Östling, Robert
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F kurfali-ostling-2021-probing
%X Pre-trained multilingual language models have become an important building block in multilingual Natural Language Processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level knowledge across languages. This is done with a systematic evaluation on a broader set of discourse-level tasks than has been previously been assembled. We find that the XLM-RoBERTa family of models consistently show the best performance, by simultaneously being good monolingual models and degrading relatively little in a zero-shot setting. Our results also indicate that model distillation may hurt the ability of cross-lingual transfer of sentence representations, while language dissimilarity at most has a modest effect. We hope that our test suite, covering 5 tasks with a total of 22 languages in 10 distinct families, will serve as a useful evaluation platform for multilingual performance at and beyond the sentence level.
%R 10.18653/v1/2021.repl4nlp-1.2
%U https://aclanthology.org/2021.repl4nlp-1.2
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.2
%P 8-19

Markdown (Informal)

[Probing Multilingual Language Models for Discourse](https://aclanthology.org/2021.repl4nlp-1.2) (Kurfalı & Östling, RepL4NLP 2021)

• Probing Multilingual Language Models for Discourse (Kurfalı & Östling, RepL4NLP 2021)

ACL

• Murathan Kurfalı and Robert Östling. 2021. Probing Multilingual Language Models for Discourse. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 8–19, Online. Association for Computational Linguistics.