@inproceedings{chatterjee-etal-2026-mosaic,
title = "Mosaic: Automated Intent Description Generation for Multi-Label Classification",
author = "Chatterjee, Ajay and
Crestan, Eric and
Saha, Raunak and
Mordoch, Rotem and
Acharyya, Swarnangsu",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.33/",
pages = "545--556",
ISBN = "979-8-89176-460-6",
abstract = "Traditional intent classifiers map utterances directly to intent categories using labeled examples. In contrast, LLM-assisted zero-shot intent classifiers rely on natural language descriptions alongside intent labels to determine the most appropriate categories for a given utterance. As intent taxonomies grow and evolve, descriptions must define clear boundaries among overlapping intent categories. Maintaining them is costly because it requires domain expertise and continual updates to keep pace with changing product and user behavior. We present MOSAIC (Multi-label Ontology Synthesis for Automated Intent Classification), a deployed system that automatically generates and updates intent descriptions for an existing taxonomy. MOSAIC analyzes unlabeled user utterances to identify coherent clusters. It associates cluster-level evidence with the existing intent taxonomy. Then, it synthesizes discriminative descriptions that define each category{'}s semantic boundary. On a 140-class production deployment, MOSAIC approaches the quality of expert-written descriptions while reducing taxonomy revision time from 2-4 weeks to less than 30 minutes. On the public NLU++ and Multi{\textthreesuperior}NLU++ benchmark datasets, MOSAIC-generated descriptions do match or exceed the performance of expert-written descriptions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatterjee-etal-2026-mosaic">
<titleInfo>
<title>Mosaic: Automated Intent Description Generation for Multi-Label Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ajay</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Crestan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raunak</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Mordoch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swarnangsu</namePart>
<namePart type="family">Acharyya</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Traditional intent classifiers map utterances directly to intent categories using labeled examples. In contrast, LLM-assisted zero-shot intent classifiers rely on natural language descriptions alongside intent labels to determine the most appropriate categories for a given utterance. As intent taxonomies grow and evolve, descriptions must define clear boundaries among overlapping intent categories. Maintaining them is costly because it requires domain expertise and continual updates to keep pace with changing product and user behavior. We present MOSAIC (Multi-label Ontology Synthesis for Automated Intent Classification), a deployed system that automatically generates and updates intent descriptions for an existing taxonomy. MOSAIC analyzes unlabeled user utterances to identify coherent clusters. It associates cluster-level evidence with the existing intent taxonomy. Then, it synthesizes discriminative descriptions that define each category’s semantic boundary. On a 140-class production deployment, MOSAIC approaches the quality of expert-written descriptions while reducing taxonomy revision time from 2-4 weeks to less than 30 minutes. On the public NLU++ and Multi³NLU++ benchmark datasets, MOSAIC-generated descriptions do match or exceed the performance of expert-written descriptions.</abstract>
<identifier type="citekey">chatterjee-etal-2026-mosaic</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>545</start>
<end>556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mosaic: Automated Intent Description Generation for Multi-Label Classification
%A Chatterjee, Ajay
%A Crestan, Eric
%A Saha, Raunak
%A Mordoch, Rotem
%A Acharyya, Swarnangsu
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F chatterjee-etal-2026-mosaic
%X Traditional intent classifiers map utterances directly to intent categories using labeled examples. In contrast, LLM-assisted zero-shot intent classifiers rely on natural language descriptions alongside intent labels to determine the most appropriate categories for a given utterance. As intent taxonomies grow and evolve, descriptions must define clear boundaries among overlapping intent categories. Maintaining them is costly because it requires domain expertise and continual updates to keep pace with changing product and user behavior. We present MOSAIC (Multi-label Ontology Synthesis for Automated Intent Classification), a deployed system that automatically generates and updates intent descriptions for an existing taxonomy. MOSAIC analyzes unlabeled user utterances to identify coherent clusters. It associates cluster-level evidence with the existing intent taxonomy. Then, it synthesizes discriminative descriptions that define each category’s semantic boundary. On a 140-class production deployment, MOSAIC approaches the quality of expert-written descriptions while reducing taxonomy revision time from 2-4 weeks to less than 30 minutes. On the public NLU++ and Multi³NLU++ benchmark datasets, MOSAIC-generated descriptions do match or exceed the performance of expert-written descriptions.
%U https://aclanthology.org/2026.emnlp-industry.33/
%P 545-556
Markdown (Informal)
[Mosaic: Automated Intent Description Generation for Multi-Label Classification](https://aclanthology.org/2026.emnlp-industry.33/) (Chatterjee et al., EMNLP 2026)
ACL