<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-wang-2026-new">
    <titleInfo>
        <title>New Intent Discovery: From Local Relations to Global Structure</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bang</namePart>
        <namePart type="family">Wang</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>New Intent Discovery (NID) aims to uncover unseen intent categories from unlabeled user queries, with the core objective of learning an intent representation space with a clear clustering structure. However, in the absence of explicit supervision, how to reliably form a global clustering structure remains challenging. To address this issue, we start from the constituent units of the global structure, namely local relations, and introduce more accessible and more stable forms of local supervision. Based on this idea, we propose LR2GS, which directly trains the intent encoder by leveraging multiple complementary local supervision signals, allowing local constraints to continuously act on the training process and thereby progressively shaping a well-separated global intent structure. Extensive experimental results demonstrate that LR2GS achieves state-of-the-art performance in both unsupervised and semi-supervised settings.</abstract>
    <identifier type="citekey">chen-wang-2026-new</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1547/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>35282</start>
            <end>35298</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T New Intent Discovery: From Local Relations to Global Structure
%A Chen, Peng
%A Wang, Bang
%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 chen-wang-2026-new
%X New Intent Discovery (NID) aims to uncover unseen intent categories from unlabeled user queries, with the core objective of learning an intent representation space with a clear clustering structure. However, in the absence of explicit supervision, how to reliably form a global clustering structure remains challenging. To address this issue, we start from the constituent units of the global structure, namely local relations, and introduce more accessible and more stable forms of local supervision. Based on this idea, we propose LR2GS, which directly trains the intent encoder by leveraging multiple complementary local supervision signals, allowing local constraints to continuously act on the training process and thereby progressively shaping a well-separated global intent structure. Extensive experimental results demonstrate that LR2GS achieves state-of-the-art performance in both unsupervised and semi-supervised settings.
%U https://aclanthology.org/2026.emnlp-main.1547/
%P 35282-35298

Markdown (Informal)

[New Intent Discovery: From Local Relations to Global Structure](https://aclanthology.org/2026.emnlp-main.1547/) (Chen & Wang, EMNLP 2026)

• New Intent Discovery: From Local Relations to Global Structure (Chen & Wang, EMNLP 2026)

ACL

• Peng Chen and Bang Wang. 2026. New Intent Discovery: From Local Relations to Global Structure. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 35282–35298, Budapest, Hungary. Association for Computational Linguistics.