@inproceedings{zve-etal-2026-noise,
title = "From Noise to Signal: When Outliers Seed New Topics",
author = "Zve, Evangelia and
Bourgne, Gauvain and
Icard, Benjamin and
Ganascia, Jean-Gabriel",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.596/",
doi = "10.63317/5c6zvq4nbjdq",
pages = "7523--7533",
abstract = "Outliers in dynamic topic modeling are often discarded as noise, yet some act as early signals of emerging topics. We introduce a temporal taxonomy of news document trajectories that distinguishes anticipatory outliers, documents that appear before a topic forms but later integrate into it, from those that reinforce existing topics or remain isolated. This taxonomy bridges weak-signal detection and dynamic topic modeling, clarifying how individual articles anticipate, initiate, or drift within evolving clusters. We implement it within a cumulative clustering framework using document- embeddings from eleven state-of-the-art language models and apply it retrospectively to HydroNewsFr, a French news corpus on the hydrogen economy curated for this study. Inter-model agreement on anticipatory outliers indicates that a small high-agreement subset yields robust confidence estimates. Complementary qualitative case studies further demonstrate their potential value as early indicators of emerging narratives. All reproducibility materials and results are available at \url{https://anonymous.4open.science/status/lrec_from_noise_to_signal-B721}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zve-etal-2026-noise">
<titleInfo>
<title>From Noise to Signal: When Outliers Seed New Topics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evangelia</namePart>
<namePart type="family">Zve</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gauvain</namePart>
<namePart type="family">Bourgne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Icard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Gabriel</namePart>
<namePart type="family">Ganascia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Outliers in dynamic topic modeling are often discarded as noise, yet some act as early signals of emerging topics. We introduce a temporal taxonomy of news document trajectories that distinguishes anticipatory outliers, documents that appear before a topic forms but later integrate into it, from those that reinforce existing topics or remain isolated. This taxonomy bridges weak-signal detection and dynamic topic modeling, clarifying how individual articles anticipate, initiate, or drift within evolving clusters. We implement it within a cumulative clustering framework using document- embeddings from eleven state-of-the-art language models and apply it retrospectively to HydroNewsFr, a French news corpus on the hydrogen economy curated for this study. Inter-model agreement on anticipatory outliers indicates that a small high-agreement subset yields robust confidence estimates. Complementary qualitative case studies further demonstrate their potential value as early indicators of emerging narratives. All reproducibility materials and results are available at https://anonymous.4open.science/status/lrec_from_noise_to_signal-B721.</abstract>
<identifier type="citekey">zve-etal-2026-noise</identifier>
<identifier type="doi">10.63317/5c6zvq4nbjdq</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.596/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7523</start>
<end>7533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Noise to Signal: When Outliers Seed New Topics
%A Zve, Evangelia
%A Bourgne, Gauvain
%A Icard, Benjamin
%A Ganascia, Jean-Gabriel
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F zve-etal-2026-noise
%X Outliers in dynamic topic modeling are often discarded as noise, yet some act as early signals of emerging topics. We introduce a temporal taxonomy of news document trajectories that distinguishes anticipatory outliers, documents that appear before a topic forms but later integrate into it, from those that reinforce existing topics or remain isolated. This taxonomy bridges weak-signal detection and dynamic topic modeling, clarifying how individual articles anticipate, initiate, or drift within evolving clusters. We implement it within a cumulative clustering framework using document- embeddings from eleven state-of-the-art language models and apply it retrospectively to HydroNewsFr, a French news corpus on the hydrogen economy curated for this study. Inter-model agreement on anticipatory outliers indicates that a small high-agreement subset yields robust confidence estimates. Complementary qualitative case studies further demonstrate their potential value as early indicators of emerging narratives. All reproducibility materials and results are available at https://anonymous.4open.science/status/lrec_from_noise_to_signal-B721.
%R 10.63317/5c6zvq4nbjdq
%U https://aclanthology.org/2026.lrec-1.596/
%U https://doi.org/10.63317/5c6zvq4nbjdq
%P 7523-7533
Markdown (Informal)
[From Noise to Signal: When Outliers Seed New Topics](https://aclanthology.org/2026.lrec-1.596/) (Zve et al., LREC 2026)
ACL
- Evangelia Zve, Gauvain Bourgne, Benjamin Icard, and Jean-Gabriel Ganascia. 2026. From Noise to Signal: When Outliers Seed New Topics. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7523–7533, Palma de Mallorca, Spain. ELRA Language Resource Association.