<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-varda-marelli-2024-emergence">
    <titleInfo>
        <title>The Emergence of Semantic Units in Massively Multilingual Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="given">Gregor</namePart>
        <namePart type="family">de Varda</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marco</namePart>
        <namePart type="family">Marelli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nicoletta</namePart>
            <namePart type="family">Calzolari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Veronique</namePart>
            <namePart type="family">Hoste</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alessandro</namePart>
            <namePart type="family">Lenci</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sakriani</namePart>
            <namePart type="family">Sakti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nianwen</namePart>
            <namePart type="family">Xue</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA and ICCL</publisher>
            <place>
                <placeTerm type="text">Torino, Italia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Massively multilingual models can process text in several languages relying on a shared set of parameters; however, little is known about the encoding of multilingual information in single network units. In this work, we study how two semantic variables, namely valence and arousal, are processed in the latent dimensions of mBERT and XLM-R across 13 languages. We report a significant cross-lingual overlap in the individual neurons processing affective information, which is more pronounced when considering XLM-R vis-à-vis mBERT. Furthermore, we uncover a positive relationship between cross-lingual alignment and performance, where the languages that rely more heavily on a shared cross-lingual neural substrate achieve higher performance scores in semantic encoding.</abstract>
    <identifier type="citekey">de-varda-marelli-2024-emergence</identifier>
    <location>
        <url>https://aclanthology.org/2024.lrec-main.1382/</url>
    </location>
    <part>
        <date>2024-05</date>
        <extent unit="page">
            <start>15910</start>
            <end>15921</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The Emergence of Semantic Units in Massively Multilingual Models
%A de Varda, Andrea Gregor
%A Marelli, Marco
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F de-varda-marelli-2024-emergence
%X Massively multilingual models can process text in several languages relying on a shared set of parameters; however, little is known about the encoding of multilingual information in single network units. In this work, we study how two semantic variables, namely valence and arousal, are processed in the latent dimensions of mBERT and XLM-R across 13 languages. We report a significant cross-lingual overlap in the individual neurons processing affective information, which is more pronounced when considering XLM-R vis-à-vis mBERT. Furthermore, we uncover a positive relationship between cross-lingual alignment and performance, where the languages that rely more heavily on a shared cross-lingual neural substrate achieve higher performance scores in semantic encoding.
%U https://aclanthology.org/2024.lrec-main.1382/
%P 15910-15921

Markdown (Informal)

[The Emergence of Semantic Units in Massively Multilingual Models](https://aclanthology.org/2024.lrec-main.1382/) (de Varda & Marelli, LREC-COLING 2024)

• The Emergence of Semantic Units in Massively Multilingual Models (de Varda & Marelli, LREC-COLING 2024)

ACL

• Andrea Gregor de Varda and Marco Marelli. 2024. The Emergence of Semantic Units in Massively Multilingual Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15910–15921, Torino, Italia. ELRA and ICCL.