@inproceedings{zve-etal-2026-predicting,
title = "Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space",
author = "Zve, Evangelia and
Bourgne, Gauvain and
Ganascia, Jean-Gabriel",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.94/",
pages = "1898--1913",
ISBN = "979-8-89176-444-6",
abstract = "Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such *anticipatory outliers* can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, $F_1$ rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76{--}0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier{'}s position in embedding space."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zve-etal-2026-predicting">
<titleInfo>
<title>Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space</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">Jean-Gabriel</namePart>
<namePart type="family">Ganascia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such *anticipatory outliers* can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, F₁ rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76–0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier’s position in embedding space.</abstract>
<identifier type="citekey">zve-etal-2026-predicting</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.94/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1898</start>
<end>1913</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space
%A Zve, Evangelia
%A Bourgne, Gauvain
%A Ganascia, Jean-Gabriel
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F zve-etal-2026-predicting
%X Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such *anticipatory outliers* can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, F₁ rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76–0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier’s position in embedding space.
%U https://aclanthology.org/2026.findings-aacl.94/
%P 1898-1913
Markdown (Informal)
[Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space](https://aclanthology.org/2026.findings-aacl.94/) (Zve et al., Findings 2026)
ACL