[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-238418-105":53,"doc-detail-238418-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","towards-automated-recipe-genre-classification-3a2m-cooking-recipe-dataset","Towards Automated Recipe Genre Classification - 3A2M+ Cooking Recipe Dataset","","Automated classification of online cooking recipes by genre is hindered by limited labeled data and the difficulty of mapping recipe descriptions to consistent food categories. This work introduces the “Assorted, Archetypal, and Annotated Two Million Extended (3A2M+) Cooking Recipe Dataset,” containing two million recipes annotated with genre labels and extended named entities extracted from directions. The 3A2M+ pipeline expands NER coverage using two NER extraction tools to recover missing entities such as heat, time, and process. Experiments combine traditional ML, deep learning, and pretrained language models, achieving 98.6% overall accuracy.",{"@graph":63,"@context":123},[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/towards-automated-recipe-genre-classification-3a2m-cooking-recipe-dataset/238418/",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/towards-automated-recipe-genre-classification-3a2m-cooking-recipe-dataset/238418.png","ImageObject",442,249,{"name":88,"@type":89},"Riley","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-28","2026-09-11",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",13,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115,119],{"name":106,"@type":107,"acceptedAnswer":108},"What problem does the study address in recipe genre classification?","Question",{"text":109,"@type":110},"It tackles the challenge of categorizing online recipes into appropriate genres despite a lack of adequate labeled data and inconsistencies in subjective genre labeling.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"What is the 3A2M+ dataset and what does it contain?",{"text":114,"@type":110},"The 3A2M+ dataset contains two million cooking recipes labeled with nine genre categories and includes extended named entities extracted from recipe descriptions and directions.",{"name":116,"@type":107,"acceptedAnswer":117},"How does the proposed pipeline improve Named Entity Recognition for recipes?",{"text":118,"@type":110},"The 3A2M+ pipeline extends the NER list by using two NER extraction tools to capture named entities that are missing in directions, such as heat, time, or process.",{"name":120,"@type":107,"acceptedAnswer":121},"What model performance is reported for genre classification?",{"text":122,"@type":110},"The study reports 98.6% overall accuracy, and notes that pretrained language models such as DistilBERT and RoBERTa are effective, with the title feature playing a particularly significant role.","https://schema.org",{"og:url":78,"og:type":125,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":127,"canonical":78},"index,follow",{"doc_id":129,"site_id":56},238418,1791736798,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":88,"user_avatar":134,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":140,"language":141,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":61,"update_tm":145,"read_time":146},1374391975076,"https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051","arXiv :2310 . 15693v1 [ cs .CL] 24 Oct 2023  \nSpringer Nature 2021 LATEX template  \nTowards Automated Recipe Genre Classification using Semi-Supervised Learning  \nNazmus Sakib 1*†, G. M. Shahariar2†, Md. Mohsinul Kabir 1 , Md.  \nKamrul Hasan 1 and Hasan Mahmud 1*  \n1* SSL Lab, Dept. of CSE, Islamic University of Technology, Dhaka,  \nBangladesh.  \n2Dept. of CSE, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh.  \n*Corresponding author(s). E-mail(s): [nazmussakib009@gmail.com](nazmussakib009@gmail.com) ; [hasan@iut-dhaka.edu](hasan@iut-dhaka.edu) ;  \nContributing authors: sshibli745@gmail,com ; [mohsinulkabir@iut-dhaka.edu](mohsinulkabir@iut-dhaka.edu) ; [hasank@iut-dhaka.edu](hasank@iut-dhaka.edu) ;  \n†These authors contributed equally to this work.  \nAbstract  \nSharing cooking recipes is a great way to exchange culinary ideas and provide instructions for food preparation. However, categorizing raw recipes found online into appropriate food genres can be challenging due to a lack of adequate labeled data. In this study, we present a dataset named the “Assorted, Archetypal, and Annotated Two Million Extended (3A2M+) Cooking Recipe Dataset” that contains two million culinary recipes labeled in respective categories with extended named entities extracted from recipe descriptions. This collection of data includes various features such as title, NER, directions, and extended NER, as well as nine different labels representing genres including bakery, drinks, non-veg, vegetables, fast food, cereals, meals, sides, and fusions. The proposed pipeline named 3A2M+ extends the size of the Named Entity Recognition (NER) list to address missing named entities like heat, time or process from the recipe directions using two NER extraction tools. 3A2M+ dataset provides a comprehensive solution to the various challenging recipe-related tasks, including classification, named entity recognition, and recipe generation. Furthermore, we have demonstrated traditional machine learning, deep learning  \nSpringer Nature 2021 LATEX template  \n2 Towards Automated Recipe Genre Classification  \nand pre-trained language models to classify the recipes into their corresponding genre and achieved an overall accuracy of 98.6% . Our investigation indicates that the title feature played a more significant role in classifying the genre.  \nKeywords: Named Entity Recognition (NER), Annotation, Active Learning, 3A2M, Recipe dataset, Human-in-the-loop (HITL), Recipe classification, RecipeNLG, RoBERTa, DistilBERT  \n1 Introduction  \nFood recipe classification is a crucial aspect of understanding and organizing recipe data, particularly in the field of machine learning and deep learning. With the growing availability of large food recipe datasets (RecipeNLG [1] and recipe 1M+ [2]) on the internet, researchers have been able to train and test deep learning models in the culinary domain [3, 4] . Recipe data includes a wealth of information, including ingredients, cooking instructions, recipe titles, and categories, that can be used to train machine learning models.  \nThe primary goal of recipe classification is to make it easier for users to find alternative recipes based on their preferred genre [5] . The classification of food recipes into genres makes it easier for users to find recipes based on their preferences and tastes, as well as enhancing the search functionality of online recipe databases. Recipe genre classification allows the creation of recommendation and recipe generation systems that can make better suggestions to users based on their preferred cuisine or ingredients. However, classifying recipes into different genres can be subjective and based on personal opinions, which can lead to inconsistencies in the classification process. Classifying recipes into few genres can result in oversimplification, while classifying recipes into too many genres can make it difficult for users to find the recipe they are looking for [5–8] . Therefore, in t","cbCaig9uZ5dcci6w","https://ap.wps.com/l/cbCaig9uZ5dcci6w","pdf",531918,29,"English","# Abstract\n# Keywords\n# Introduction\n## Dataset and NER extension (3A2M+)\n## Genre classification results\n## Applications to related recipe tasks","[{\"question\":\"What problem does the study address in recipe genre classification?\",\"answer\":\"It tackles the challenge of categorizing online recipes into appropriate genres despite a lack of adequate labeled data and inconsistencies in subjective genre labeling.\"},{\"question\":\"What is the 3A2M+ dataset and what does it contain?\",\"answer\":\"The 3A2M+ dataset contains two million cooking recipes labeled with nine genre categories and includes extended named entities extracted from recipe descriptions and directions.\"},{\"question\":\"How does the proposed pipeline improve Named Entity Recognition for recipes?\",\"answer\":\"The 3A2M+ pipeline extends the NER list by using two NER extraction tools to capture named entities that are missing in directions, such as heat, time, or process.\"},{\"question\":\"What model performance is reported for genre classification?\",\"answer\":\"The study reports 98.6% overall accuracy, and notes that pretrained language models such as DistilBERT and RoBERTa are effective, with the title feature playing a particularly significant role.\"}]","Towards Automated Recipe Genre Classification - 3A2M+ Cooking Recipe Dataset | PDF",1789135315,10]