@inproceedings{golobokov-etal-2022-deepgen,
title = "{D}eep{G}en: Diverse Search Ad Generation and Real-Time Customization",
author = "Golobokov, Konstantin and
Chai, Junyi and
Dong, Victor Ye and
Gu, Mandy and
Chi, Bingyu and
Cao, Jie and
Yan, Yulan and
Liu, Yi",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.19",
doi = "10.18653/v1/2022.emnlp-demos.19",
pages = "191--199",
abstract = "Demo: \url{https://youtu.be/WQLL93TPB-cAbstract:We} present DeepGen, a system deployed at web scale for automatically creating sponsored search advertisements (ads) for BingAds customers. We leverage state-of-the-art natural language generation (NLG) models to generate fluent ads from advertiser{'}s web pages in an abstractive fashion and solve practical issues such as factuality and inference speed. In addition, our system creates a customized ad in real-time in response to the user{'}s search query, therefore highlighting different aspects of the same product based on what the user is looking for. To achieve this, our system generates a diverse choice of smaller pieces of the ad ahead of time and, at query time, selects the most relevant ones to be stitched into a complete ad. We improve generation diversity by training a controllable NLG model to generate multiple ads for the same web page highlighting different selling points. Our system design further improves diversity horizontally by first running an ensemble of generation models trained with different objectives and then using a diversity sampling algorithm to pick a diverse subset of generation results for online selection. Experimental results show the effectiveness of our proposed system design. Our system is currently deployed in production, serving {\textasciitilde}4{\%} of global ads served in Bing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="golobokov-etal-2022-deepgen">
<titleInfo>
<title>DeepGen: Diverse Search Ad Generation and Real-Time Customization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Golobokov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="given">Ye</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandy</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingyu</namePart>
<namePart type="family">Chi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Demo: https://youtu.be/WQLL93TPB-cAbstract:We present DeepGen, a system deployed at web scale for automatically creating sponsored search advertisements (ads) for BingAds customers. We leverage state-of-the-art natural language generation (NLG) models to generate fluent ads from advertiser’s web pages in an abstractive fashion and solve practical issues such as factuality and inference speed. In addition, our system creates a customized ad in real-time in response to the user’s search query, therefore highlighting different aspects of the same product based on what the user is looking for. To achieve this, our system generates a diverse choice of smaller pieces of the ad ahead of time and, at query time, selects the most relevant ones to be stitched into a complete ad. We improve generation diversity by training a controllable NLG model to generate multiple ads for the same web page highlighting different selling points. Our system design further improves diversity horizontally by first running an ensemble of generation models trained with different objectives and then using a diversity sampling algorithm to pick a diverse subset of generation results for online selection. Experimental results show the effectiveness of our proposed system design. Our system is currently deployed in production, serving ~4% of global ads served in Bing.</abstract>
<identifier type="citekey">golobokov-etal-2022-deepgen</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.19</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.19</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>191</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeepGen: Diverse Search Ad Generation and Real-Time Customization
%A Golobokov, Konstantin
%A Chai, Junyi
%A Dong, Victor Ye
%A Gu, Mandy
%A Chi, Bingyu
%A Cao, Jie
%A Yan, Yulan
%A Liu, Yi
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F golobokov-etal-2022-deepgen
%X Demo: https://youtu.be/WQLL93TPB-cAbstract:We present DeepGen, a system deployed at web scale for automatically creating sponsored search advertisements (ads) for BingAds customers. We leverage state-of-the-art natural language generation (NLG) models to generate fluent ads from advertiser’s web pages in an abstractive fashion and solve practical issues such as factuality and inference speed. In addition, our system creates a customized ad in real-time in response to the user’s search query, therefore highlighting different aspects of the same product based on what the user is looking for. To achieve this, our system generates a diverse choice of smaller pieces of the ad ahead of time and, at query time, selects the most relevant ones to be stitched into a complete ad. We improve generation diversity by training a controllable NLG model to generate multiple ads for the same web page highlighting different selling points. Our system design further improves diversity horizontally by first running an ensemble of generation models trained with different objectives and then using a diversity sampling algorithm to pick a diverse subset of generation results for online selection. Experimental results show the effectiveness of our proposed system design. Our system is currently deployed in production, serving ~4% of global ads served in Bing.
%R 10.18653/v1/2022.emnlp-demos.19
%U https://aclanthology.org/2022.emnlp-demos.19
%U https://doi.org/10.18653/v1/2022.emnlp-demos.19
%P 191-199
Markdown (Informal)
[DeepGen: Diverse Search Ad Generation and Real-Time Customization](https://aclanthology.org/2022.emnlp-demos.19) (Golobokov et al., EMNLP 2022)
ACL
- Konstantin Golobokov, Junyi Chai, Victor Ye Dong, Mandy Gu, Bingyu Chi, Jie Cao, Yulan Yan, and Yi Liu. 2022. DeepGen: Diverse Search Ad Generation and Real-Time Customization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 191–199, Abu Dhabi, UAE. Association for Computational Linguistics.