@inproceedings{wei-wu-2026-diverse,
title = "From Diverse Outputs to Structured Set: Semantic Planning Enables Parallel Advertising Text Generation",
author = "Wei, Penghui and
wu, Jiayu",
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.185/",
pages = "3127--3136",
ISBN = "979-8-89176-460-6",
abstract = "An advertising platform typically generates a diverse candidate set of text creatives for each ad and then employs personalized online ranking to estimate the top-performing one for final display. Conventionally, the diversity is treated as a by-product during the stochastic decoding process rather than a training objective, which results in suboptimal outputs due to the lack of explicit modeling for semantic coverage. In this paper we reformulate ad text generation as a set-level modeling problem, and propose a parallel generation framework that optimizes the diversity objective with set-level alignment. By explicitly decomposing an ad{'}s content structure into semantic-independent perspectives via a planning mechanism, our framework generates the entire set of text creatives in parallel based on the planned semantics, which also takes full advantage of parallelizability to enable high-throughput industrial deployment. It is optimized through a set-level alignment stage that encourages the overall semantic coverage and penalizes the redundancy among the candidates. Comprehensive experiments on benchmark dataset show that our framework achieves better set-level quality and diversity, as well as significantly improving generation throughput, demonstrating its superiority on both generation quality and inference speed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-wu-2026-diverse">
<titleInfo>
<title>From Diverse Outputs to Structured Set: Semantic Planning Enables Parallel Advertising Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Penghui</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayu</namePart>
<namePart type="family">wu</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>An advertising platform typically generates a diverse candidate set of text creatives for each ad and then employs personalized online ranking to estimate the top-performing one for final display. Conventionally, the diversity is treated as a by-product during the stochastic decoding process rather than a training objective, which results in suboptimal outputs due to the lack of explicit modeling for semantic coverage. In this paper we reformulate ad text generation as a set-level modeling problem, and propose a parallel generation framework that optimizes the diversity objective with set-level alignment. By explicitly decomposing an ad’s content structure into semantic-independent perspectives via a planning mechanism, our framework generates the entire set of text creatives in parallel based on the planned semantics, which also takes full advantage of parallelizability to enable high-throughput industrial deployment. It is optimized through a set-level alignment stage that encourages the overall semantic coverage and penalizes the redundancy among the candidates. Comprehensive experiments on benchmark dataset show that our framework achieves better set-level quality and diversity, as well as significantly improving generation throughput, demonstrating its superiority on both generation quality and inference speed.</abstract>
<identifier type="citekey">wei-wu-2026-diverse</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.185/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3127</start>
<end>3136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Diverse Outputs to Structured Set: Semantic Planning Enables Parallel Advertising Text Generation
%A Wei, Penghui
%A wu, Jiayu
%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 wei-wu-2026-diverse
%X An advertising platform typically generates a diverse candidate set of text creatives for each ad and then employs personalized online ranking to estimate the top-performing one for final display. Conventionally, the diversity is treated as a by-product during the stochastic decoding process rather than a training objective, which results in suboptimal outputs due to the lack of explicit modeling for semantic coverage. In this paper we reformulate ad text generation as a set-level modeling problem, and propose a parallel generation framework that optimizes the diversity objective with set-level alignment. By explicitly decomposing an ad’s content structure into semantic-independent perspectives via a planning mechanism, our framework generates the entire set of text creatives in parallel based on the planned semantics, which also takes full advantage of parallelizability to enable high-throughput industrial deployment. It is optimized through a set-level alignment stage that encourages the overall semantic coverage and penalizes the redundancy among the candidates. Comprehensive experiments on benchmark dataset show that our framework achieves better set-level quality and diversity, as well as significantly improving generation throughput, demonstrating its superiority on both generation quality and inference speed.
%U https://aclanthology.org/2026.emnlp-industry.185/
%P 3127-3136
Markdown (Informal)
[From Diverse Outputs to Structured Set: Semantic Planning Enables Parallel Advertising Text Generation](https://aclanthology.org/2026.emnlp-industry.185/) (Wei & wu, EMNLP 2026)
ACL