<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-xing-2026-typed">
    <titleInfo>
        <title>Typed Relation Path Geometry in Sentence Embedding Spaces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mingyue</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyang</namePart>
        <namePart type="family">Xing</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Lexical relations are not only labels on pairs of concepts: they are directed typed movements that can form paths. We study whether sentence embedding spaces preserve this structure at the level of individual relation instances. By representing two-hop lexical chains as composed movements on the normalised embedding sphere, we test whether true chains form more coherent routes than matched false-middle alternatives. Across controlled lexical path experiments, real chains exhibit a robust path signal, including for mixed relation compositions, and the composed movements retain information about ordered relation type. Beyond diagnosis, the same path geometry aligns with independent distributional context shifts and improves graded lexical-entailment transfer, indicating that it captures reusable lexical structure rather than a task-specific artefact.</abstract>
    <identifier type="citekey">liu-xing-2026-typed</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2530/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>57548</start>
            <end>57564</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Typed Relation Path Geometry in Sentence Embedding Spaces
%A Liu, Mingyue
%A Xing, Ziyang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-xing-2026-typed
%X Lexical relations are not only labels on pairs of concepts: they are directed typed movements that can form paths. We study whether sentence embedding spaces preserve this structure at the level of individual relation instances. By representing two-hop lexical chains as composed movements on the normalised embedding sphere, we test whether true chains form more coherent routes than matched false-middle alternatives. Across controlled lexical path experiments, real chains exhibit a robust path signal, including for mixed relation compositions, and the composed movements retain information about ordered relation type. Beyond diagnosis, the same path geometry aligns with independent distributional context shifts and improves graded lexical-entailment transfer, indicating that it captures reusable lexical structure rather than a task-specific artefact.
%U https://aclanthology.org/2026.emnlp-main.2530/
%P 57548-57564

Markdown (Informal)

[Typed Relation Path Geometry in Sentence Embedding Spaces](https://aclanthology.org/2026.emnlp-main.2530/) (Liu & Xing, EMNLP 2026)

• Typed Relation Path Geometry in Sentence Embedding Spaces (Liu & Xing, EMNLP 2026)

ACL

• Mingyue Liu and Ziyang Xing. 2026. Typed Relation Path Geometry in Sentence Embedding Spaces. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 57548–57564, Budapest, Hungary. Association for Computational Linguistics.