[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-289946-105":59,"doc-detail-289946-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","discriminative-topic-mining-via-category-name-guided-text-embedding-abstract-and-introduction","Discriminative Topic Mining via Category-Name Guided Text Embedding - Abstract and Introduction","","Mining meaningful, distinctive topics from massive text corpora enables broad downstream uses, yet common topic models remain largely unsupervised and often misalign with user goals. The paper introduces discriminative topic mining, using user-provided category names as guidance to extract representative, category-distinguishing topics and terms. It presents CatE, a category-name guided text embedding method that iteratively learns a discriminative space. Experiments show high-quality, category-name-only topic discovery and benefits for weakly supervised classification and lexical entailment direction identification.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/discriminative-topic-mining-via-category-name-guided-text-embedding-abstract-and-introduction/289946/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/discriminative-topic-mining-via-category-name-guided-text-embedding-abstract-and-introduction/289946.png","ImageObject",300,407,{"name":92,"@type":93},"Pentious","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in traditional topic modeling?","Question",{"text":112,"@type":113},"Traditional topic models often ignore user guidance, producing topics that may not match a user’s interests, and they lack constraints to ensure topic distinctiveness, leading to overlapping and vague topic interpretations.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the new task proposed by the paper?",{"text":117,"@type":113},"The paper proposes discriminative topic mining, where a user provides category names as guidance so the system retrieves representative and discriminative terms for each category.",{"name":119,"@type":110,"acceptedAnswer":120},"What does the CatE method contribute?",{"text":121,"@type":113},"CatE is a category-name guided text embedding approach that uses minimal user guidance to learn a discriminative embedding space iteratively and discover category representative terms, improving downstream applications such as weakly supervised classification and lexical entailment direction identification.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},289946,1789638720,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},1374404730887,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Discriminative Topic Mining via Category-Name Guided Text  \nEmbedding  \nYu Meng 1∗, Jiaxin Huang 1∗, Guangyuan Wang 1 , Zihan Wang 1 , Chao Zhang2 , Yu Zhang 1 , Jiawei Han 1  \n1Department of Computer Science, University of Illinois at Urbana-Champaign, IL, USA  \n2 College of Computing, Georgia Institute of Technology, GA, USA  \n1 {yumeng5, jiaxinh3, gwang10, zihanw2, yuz9, [hanj}@illinois.edu](hanj}@illinois.edu 2 chaozhang@gatech.edu)[ 2](hanj}@illinois.edu 2 chaozhang@gatech.edu)[ chaozhang@gatech.edu](hanj}@illinois.edu 2 chaozhang@gatech.edu)  \nABSTRACT  \nMining a set of meaningful and distinctive topics automatically from massive text corpora has broad applications. Existing topic models, however, typically work in a purely unsupervised way, which often generate topics that do not fit users’ particular needs and yield suboptimal performance on downstream tasks. We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora. This new task not only helps a user understand clearly and distinctively the topics he/she is most interested in, but also benefits directly keyword-driven classification tasks. We develop CatE, a novel category-name guided text embedding method for discriminative topic mining, which effectively leverages minimal user guidance to learn a discriminative embedding space and discover category representative terms in an iterative manner. We conduct a comprehensive set of experiments to show that CatE mines highquality set of topics guided by category names only, and benefits a variety of downstream applications including weakly-supervised classification and lexical entailment direction identification.  \nCCS CONCEPTS  \n• Information systems → Data mining; Document topic models; Clustering and classification;  \nKEYWORDS  \nTopic Mining, Discriminative Analysis, Text Embedding, Text Classification  \nACM Reference Format:  \nYu Meng1∗, Jiaxin Huang1∗, Guangyuan Wang1 , Zihan Wang1 , Chao Zhang2 , Yu Zhang1 , Jiawei Han1 . 2020. Discriminative Topic Mining via CategoryName Guided Text Embedding. In Proceedings of The Web Conference 2020 (WWW’20), April 20–24, 2020, Taipei, Taiwan. ACM, New York, NY, USA, 11 pages. [https://doi.org/10.1145/3366423.3380278](https://doi.org/10.1145/3366423.3380278)  \n∗ Equal Contribution.  \nThis paper is published under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.  \nWWW’20, April 20–24, 2020, Taipei, Taiwan  \n© 2020 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC BY 4 .0 License.  \nACM ISBN 978-1-4503-7023-3/20/04 .  \n[https://doi.org/10.1145/3366423.3380278](https://doi.org/10.1145/3366423.3380278)  \n1 INTRODUCTION  \nTo help users effectively and efficiently comprehend a large set of text documents, it is of great interest to generate a set of meaningful and coherent topics automatically from a given corpus. Topic models [6, 19] are such unsupervised statistical tools that discover latent topics from text corpora. Due to their effectiveness in uncovering hidden semantic structure in text collections, topic models are widely used in text mining [15, 29] and information retrieval tasks [14, 52] .  \nDespite of their effectiveness, traditional topic models suffer from two noteworthy limitations: (1) Failure to incorporate user guidance. Topic models tend to retrieve the most general and prominent topics from a text collection, which may not be of a user’s particular interest, or provide a skewed and biased summarization of the corpus. (2) Failure to enforce distinctiveness among retrieved topics. Concepts are most effectively interpreted via their uniquely defining features. For example, Egypt is known for pyramids and China is known for the Great Wall. Topic models, however, do not imposedisrimi","cbCaigG8tMsAuj5m","https://ap.wps.com/l/cbCaigG8tMsAuj5m","pdf",1155292,11,"English","# Abstract\n# Introduction\n## Unsupervised topic models and their limitations\n## Proposed discriminative topic mining task\n## Prior work on supervised topic models","[{\"question\":\"What problem does the paper address in traditional topic modeling?\",\"answer\":\"Traditional topic models often ignore user guidance, producing topics that may not match a user’s interests, and they lack constraints to ensure topic distinctiveness, leading to overlapping and vague topic interpretations.\"},{\"question\":\"What is the new task proposed by the paper?\",\"answer\":\"The paper proposes discriminative topic mining, where a user provides category names as guidance so the system retrieves representative and discriminative terms for each category.\"},{\"question\":\"What does the CatE method contribute?\",\"answer\":\"CatE is a category-name guided text embedding approach that uses minimal user guidance to learn a discriminative embedding space iteratively and discover category representative terms, improving downstream applications such as weakly supervised classification and lexical entailment direction identification.\"}]","Discriminative Topic Mining via Category-Name Guided Text Embedding - Abstract and Introduction | PDF",28]