<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kokot-poelman-2025-type">
    <titleInfo>
        <title>Type and Complexity Signals in Multilingual Question Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Robin</namePart>
        <namePart type="family">Kokot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wessel</namePart>
        <namePart type="family">Poelman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="given">Ifeoluwa</namePart>
            <namePart type="family">Adelani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Catherine</namePart>
            <namePart type="family">Arnett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Duygu</namePart>
            <namePart type="family">Ataman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tyler</namePart>
            <namePart type="given">A</namePart>
            <namePart type="family">Chang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hila</namePart>
            <namePart type="family">Gonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rahul</namePart>
            <namePart type="family">Raja</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabian</namePart>
            <namePart type="family">Schmidt</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Stap</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiayi</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhuo, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-345-6</identifier>
    </relatedItem>
    <abstract>This work investigates how a multilingual transformer model represents morphosyntactic properties of questions. We introduce the Question Type and Complexity (QTC) dataset with sentences across seven languages, annotated with type information and complexity metrics including dependency length, tree depth, and lexical density. Our evaluation extends probing methods to regression labels with selectivity controls to quantify gains in generalizability. We compare layer-wise probes on frozen Glot500-m (Imani et al., 2023) representations against subword TF-IDF baselines, and a fine-tuned model. Results show that statistical features classify questions well in explicitly marked languages and structural complexity prediction, while neural probes lead on individual metrics. We use these results to evaluate when contextual representations outperform statistical baselines and whether parameter updates reduce availability of pre-trained linguistic information.</abstract>
    <identifier type="citekey">kokot-poelman-2025-type</identifier>
    <identifier type="doi">10.18653/v1/2025.mrl-main.28</identifier>
    <location>
        <url>https://aclanthology.org/2025.mrl-main.28/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>411</start>
            <end>425</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Type and Complexity Signals in Multilingual Question Representations
%A Kokot, Robin
%A Poelman, Wessel
%Y Adelani, David Ifeoluwa
%Y Arnett, Catherine
%Y Ataman, Duygu
%Y Chang, Tyler A.
%Y Gonen, Hila
%Y Raja, Rahul
%Y Schmidt, Fabian
%Y Stap, David
%Y Wang, Jiayi
%S Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhuo, China
%@ 979-8-89176-345-6
%F kokot-poelman-2025-type
%X This work investigates how a multilingual transformer model represents morphosyntactic properties of questions. We introduce the Question Type and Complexity (QTC) dataset with sentences across seven languages, annotated with type information and complexity metrics including dependency length, tree depth, and lexical density. Our evaluation extends probing methods to regression labels with selectivity controls to quantify gains in generalizability. We compare layer-wise probes on frozen Glot500-m (Imani et al., 2023) representations against subword TF-IDF baselines, and a fine-tuned model. Results show that statistical features classify questions well in explicitly marked languages and structural complexity prediction, while neural probes lead on individual metrics. We use these results to evaluate when contextual representations outperform statistical baselines and whether parameter updates reduce availability of pre-trained linguistic information.
%R 10.18653/v1/2025.mrl-main.28
%U https://aclanthology.org/2025.mrl-main.28/
%U https://doi.org/10.18653/v1/2025.mrl-main.28
%P 411-425

Markdown (Informal)

[Type and Complexity Signals in Multilingual Question Representations](https://aclanthology.org/2025.mrl-main.28/) (Kokot & Poelman, MRL 2025)

• Type and Complexity Signals in Multilingual Question Representations (Kokot & Poelman, MRL 2025)

ACL

• Robin Kokot and Wessel Poelman. 2025. Type and Complexity Signals in Multilingual Question Representations. In Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pages 411–425, Suzhuo, China. Association for Computational Linguistics.