Stratified Topographic Similarity

Jean-Baptiste Sevestre; Matthieu Geist; Emmanuel Dupoux

Stratified Topographic Similarity

Jean-Baptiste Sevestre, Matthieu Geist, Emmanuel Dupoux

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Topographic Similarity (TopSim) is the most widely used metric for compositionality in emergent communication research. However, when evaluated on a class of languages where compositional structure is fully known (simple natural-language word concatenations), TopSim, along with other well-known metrics, under-reports compositionality. We investigate and trace TopSim’s failure to a distributional imbalance in pairwise object distances that grows with the input space size, and propose stratified-TopSim, a minimal fix that remains stable across settings and reliably evaluates languages of varying compositional structure, on both controlled benchmarks and emergent languages.

Anthology ID:: 2026.findings-emnlp.2006
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 42735–42744
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.2006/
DOI:
Bibkey:
Cite (ACL):: Jean-Baptiste Sevestre, Matthieu Geist, and Emmanuel Dupoux. 2026. Stratified Topographic Similarity. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42735–42744, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: Stratified Topographic Similarity (Sevestre et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.2006.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{sevestre-etal-2026-stratified,
    title = "Stratified Topographic Similarity",
    author = "Sevestre, Jean-Baptiste  and
      Geist, Matthieu  and
      Dupoux, Emmanuel",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.2006/",
    pages = "42735--42744",
    ISBN = "979-8-89176-462-0",
    abstract = "Topographic Similarity (TopSim) is the most widely used metric for compositionality in emergent communication research. However, when evaluated on a class of languages where compositional structure is fully known (simple natural-language word concatenations), TopSim, along with other well-known metrics, under-reports compositionality. We investigate and trace TopSim{'}s failure to a distributional imbalance in pairwise object distances that grows with the input space size, and propose stratified-TopSim, a minimal fix that remains stable across settings and reliably evaluates languages of varying compositional structure, on both controlled benchmarks and emergent languages."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sevestre-etal-2026-stratified">
    <titleInfo>
        <title>Stratified Topographic Similarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jean-Baptiste</namePart>
        <namePart type="family">Sevestre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthieu</namePart>
        <namePart type="family">Geist</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Emmanuel</namePart>
        <namePart type="family">Dupoux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Topographic Similarity (TopSim) is the most widely used metric for compositionality in emergent communication research. However, when evaluated on a class of languages where compositional structure is fully known (simple natural-language word concatenations), TopSim, along with other well-known metrics, under-reports compositionality. We investigate and trace TopSim’s failure to a distributional imbalance in pairwise object distances that grows with the input space size, and propose stratified-TopSim, a minimal fix that remains stable across settings and reliably evaluates languages of varying compositional structure, on both controlled benchmarks and emergent languages.</abstract>
    <identifier type="citekey">sevestre-etal-2026-stratified</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2006/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>42735</start>
            <end>42744</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Stratified Topographic Similarity
%A Sevestre, Jean-Baptiste
%A Geist, Matthieu
%A Dupoux, Emmanuel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F sevestre-etal-2026-stratified
%X Topographic Similarity (TopSim) is the most widely used metric for compositionality in emergent communication research. However, when evaluated on a class of languages where compositional structure is fully known (simple natural-language word concatenations), TopSim, along with other well-known metrics, under-reports compositionality. We investigate and trace TopSim’s failure to a distributional imbalance in pairwise object distances that grows with the input space size, and propose stratified-TopSim, a minimal fix that remains stable across settings and reliably evaluates languages of varying compositional structure, on both controlled benchmarks and emergent languages.
%U https://aclanthology.org/2026.findings-emnlp.2006/
%P 42735-42744

Download as File

Markdown (Informal)

[Stratified Topographic Similarity](https://aclanthology.org/2026.findings-emnlp.2006/) (Sevestre et al., Findings 2026)

Stratified Topographic Similarity (Sevestre et al., Findings 2026)

ACL

Jean-Baptiste Sevestre, Matthieu Geist, and Emmanuel Dupoux. 2026. Stratified Topographic Similarity. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42735–42744, Budapest, Hungary. Association for Computational Linguistics.