[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-238263-105":53,"doc-detail-238263-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","topic-driven-ensemble-for-online-advertising-generation","Topic-driven Ensemble for Online Advertising Generation","","Online advertising is a widely used way to reach target audiences, and effective banners often require strong writing and product understanding. This paper presents a neural network approach that automatically generates advertising text from given webpage sources using open data to reduce costly manual labeling. Because the collected data spans multiple subdomains with heterogeneous topics and vocabularies, quality can drop. The study addresses this with topic identification and a new ensemble method built from multiple instances of a seq2seq model, improving banner quality on a Russian dataset.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/topic-driven-ensemble-for-online-advertising-generation/238263/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/topic-driven-ensemble-for-online-advertising-generation/238263.png","ImageObject",442,249,{"name":88,"@type":89},"Stanford","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-11-01","2026-09-11",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",13,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"What problem does the paper address in online advertising generation?","Question",{"text":109,"@type":110},"It addresses the difficulty of automatically generating high-quality banner text from webpage sources, especially when open crawled data contains multiple heterogeneous subdomains.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"How does the proposed method reduce manual labeling costs?",{"text":114,"@type":110},"It trains using open data collected online, avoiding expensive procedures of manual labeling by relying on crawled source-banner pairs.",{"name":116,"@type":107,"acceptedAnswer":117},"What is the key idea behind the ensemble approach?",{"text":118,"@type":110},"The approach identifies existing topic-driven subdomains and builds an ensemble using multiple instances of a seq2seq model fine-tuned to extract topic-specific groups.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},238263,1791351749,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":8,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":79},2336477552062,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Topic-driven Ensemble for Online Advertising Generation  \nEgor Nevezhin  \nITMO University[egornevezhin@itmo.ru](egornevezhin@itmo.ru)  \nNikolay Butakov  \nITMO University [alipoov.nb@gmail.com](alipoov.nb@gmail.com)  \nMaria Khodorchenko  \nITMO University [mariyaxod@yandex.ru](mariyaxod@yandex.ru)  \nMaxim Petrov Denis Nasonov  \nITMO University ITMO University  \ndjvipmax@gmail .com denis .nasonov@gmail .com  \nAbstract  \nOnline advertising is one of the most widespread ways to reach and increase a target audience for those selling products. Usually having a form of a banner, advertising engages users into visiting a corresponding webpage. Professional generation of banners requires creative and writing skills and a basic understanding of target products. The great variety of goods presented in the online market enforce professionals to spend more and more time creating new advertisements different from existing ones. In this paper, we propose a neural network-based approach for the automatic generation of online advertising using texts from given webpages as sources. The important part of the approach is training on open data available online, which allows avoiding costly procedures of manual labeling. Collected open data consist of multiple subdomains with high data heterogeneity. The subdomains belong to different topics and vary in used vocabularies, phrases, styles that lead to reduced quality in adverts generation. We try to solve the problem of identifying existed subdomains and proposing a new ensemble approach based on exploiting multiple instances of a seq2seq model. Our experimental study on a dataset in the Russian language shows that our approach can significantly improve the quality of adverts generation.  \n1 Introduction  \nThe task of abstractive summarization assumes getting short but still a semantically relevant representation of some text. The summarization helps advertisement to catch user attention, get him or her interested, and finally to engage in the full text reading. This is especially true for online advertising when it flashes in front of eyes on most website in the Internet.  \nCrafting such short texts for online advertising requires a level of mastering and some degree of subject understanding. Humans doing this job have to read at least the base text, which describes products or services and then to spend additional time thinking of suitable describing phrase. That may be very time-consuming and thus a good option for automation.  \nModern natural language processing methods and techniques allow solving the task up to some degree of quality while still leaving space for improvement. The most advanced methods are based on neural network seq2seq models (Gehrmann et al., 2018) and consume large manually labeled datasets for supervised learning.  \nDue to being so popular and widespread, online advertising gives us an opportunity to obtain labeled data (in this particular case, a pair of the source text and banner text) using only data crawling techniques significantly decreasing human efforts needed to build a sufficient dataset for the task.  \nAt the same time, ollected open data may consist of multiple subdomains with high data heterogeneity. Moreover, what data will come from the crawling depends on advertising providers and their strategies adopted to the end-user. The subdomains belong to different topics and may vary substantially in used vocabularies, phrases, text styles. This heterogeneity may be amplified by overrepresentation of some domains while underrepresentation of others. As it will be demonstrated in our experimental study, all  \nThis work is licensed under a Creative Commons Attribution 4 .0 International Licence. Licence details: [http://](http://)[ ](http://)[creativecommons.org/licenses/by/4.0/](creativecommons.org/licenses/by/4.0/) .  \n2273  \nProceedings of the 28th International Conference on Computational Linguistics, pages 2273–2283 Barcelona, Spain (Online), December 8-13, 2020  \nment","cbCaiq3yOUs4OTZ7","https://ap.wps.com/l/cbCaiq3yOUs4OTZ7","pdf",487840,"English","# Abstract\n# 1 Introduction\n# 2 Related work","[{\"question\":\"What problem does the paper address in online advertising generation?\",\"answer\":\"It addresses the difficulty of automatically generating high-quality banner text from webpage sources, especially when open crawled data contains multiple heterogeneous subdomains.\"},{\"question\":\"How does the proposed method reduce manual labeling costs?\",\"answer\":\"It trains using open data collected online, avoiding expensive procedures of manual labeling by relying on crawled source-banner pairs.\"},{\"question\":\"What is the key idea behind the ensemble approach?\",\"answer\":\"The approach identifies existing topic-driven subdomains and builds an ensemble using multiple instances of a seq2seq model fine-tuned to extract topic-specific groups.\"}]","Topic-driven Ensemble for Online Advertising Generation | PDF",1789133158]