[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-267349-105":3,"doc-detail-267349-en":81,"detail-sidebar-cat-0-en-105":98},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","learning-analogies-and-semantic-relations-research-report","Learning Analogies and Semantic Relations - Research report","","We present a learning algorithm that derives semantic knowledge from unlabeled text using a Vector Space Model (VSM) for information retrieval. The method targets SAT-style verbal analogies of the form A:B::C:D, selecting the most analogous word pair C:D from multiple choices. Experiments on 374 college-level analogy questions yield 47% correct versus 20% random guessing. The work also addresses noun-modifier semantic relations, achieving strong F values with nearest-neighbour classification across multiple relation class settings.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/learning-analogies-and-semantic-relations-research-report/267349/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/learning-analogies-and-semantic-relations-research-report/267349.png","ImageObject",300,407,{"name":42,"@type":43},"Stanford","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-17","2026-09-14",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the report address?","Question",{"text":63,"@type":64},"It addresses learning semantic relations for SAT-style verbal analogy questions and for classifying noun-modifier pairs by the relation between the noun and modifier.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the proposed algorithm solve verbal analogy problems?",{"text":68,"@type":64},"It uses a Vector Space Model approach to identify the most analogous word pair C:D given a query pair A:B, then selects the best match among candidate choices.",{"name":70,"@type":61,"acceptedAnswer":71},"What results does the report report for analogy and noun-modifier relation tasks?",{"text":72,"@type":64},"On 374 college-level analogy questions, the algorithm reaches 47% correct (vs 20% random). For noun-modifier relations, nearest-neighbour learning achieves F values of 26.5% with 30 classes and 43.2% with 5 classes, described as state-of-the-art for these settings.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},267349,1789417509,{"code":4,"msg":82,"data":83},"success",{"doc_id":79,"user_id":84,"nickname":42,"user_avatar":85,"doc_module":4,"category_id":86,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":87,"file_id":88,"file_url":89,"file_type":90,"file_size":91,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":92,"language":93,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":94,"faqs":95,"seo_title":96,"seo_description":12,"update_tm":80,"read_time":97,"preview_page_count":4},2336477552062,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"National Research Council Canada  \nConseil national de recherches Canada  \nERB-1103 NRC-46488  \nInstitute for  \nInformation Technology  \nInstitut de technologie de l’information  \nLearning Analogies and Semantic Relations  \nPeter Turney, National Research Council Canada Michael Littman, Rutgers University  \nJuly 23, 2003  \n© Copyright 2003 by  \nNational Research Council of Canada  \nPermission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such materials is fully acknowledged.  \nNRC/ERB-1103 . Learning Analogies and Semantic Relations  \nTable of Contents  \nAbstract........................................................................................................................... 3  \n1 Introduction ............................................................................................................. 3  \n2 Motivation and Applications..................................................................................... 4  \n2.1 Ubiquity of Metaphor........................................................................................ 5  \n2.2 Evolution of Language ..................................................................................... 6  \n2.3 Noun-Modifier Semantic Relations................................................................... 6  \n3 Related Work .......................................................................................................... 7  \n3.1 Metaphor and Analogy..................................................................................... 7  \n3.2 Vector Space Model ........................................................................................ 8  \n3.3 Noun-Modifier Semantic Relations................................................................... 8  \n4 Solving Verbal Analogy Problems ........................................................................... 9  \n4.1 Analogy Problems ........................................................................................... 9  \n4.2 VSM Approach .............................................................................................. 10  \n4.3 Experiments................................................................................................... 12  \n4.3.1 Recognizing Analogies........................................................................... 12  \n4.3.2 Generating Analogies ............................................................................ 14  \n4.4 Human SAT Scores ....................................................................................... 16  \n4.5 Discussion ..................................................................................................... 17  \n5 Noun-Modifier Relations ........................................................................................ 18  \n5.1 Classes of Relations ...................................................................................... 18  \n5.2 Nearest-Neighbour Approach ........................................................................ 19  \n5.3 Experiments................................................................................................... 19  \n5.3.1 Thirty Classes ........................................................................................ 20  \n5.3.2 Five Classes .......................................................................................... 22  \n5.4 Discussion ..................................................................................................... 24  \n6 Limitations and Future Work.................................................................................. 25  \n7 Conclusion ............................................................................................................ 25  \nAcknowledgements....................................................................................................... 26  \nReferences ............................................................","cbCaierNDDfYBdaT","https://ap.wps.com/l/cbCaierNDDfYBdaT","pdf",192668,28,"English","# Abstract\n# 1 Introduction\n# 2 Motivation and Applications\n## 2.1 Ubiquity of Metaphor\n## 2.2 Evolution of Language\n## 2.3 Noun-Modifier Semantic Relations\n# 3 Related Work\n## 3.1 Metaphor and Analogy\n## 3.2 Vector Space Model\n## 3.3 Noun-Modifier Semantic Relations\n# 4 Solving Verbal Analogy Problems\n## 4.1 Analogy Problems\n## 4.2 VSM Approach\n## 4.3 Experiments\n## 4.4 Human SAT Scores\n## 4.5 Discussion\n# 5 Noun-Modifier Relations\n## 5.1 Classes of Relations\n## 5.2 Nearest-Neighbour Approach\n## 5.3 Experiments\n## 5.4 Discussion\n# 6 Limitations and Future Work\n# 7 Conclusion\n# Acknowledgements\n# References","[{\"question\":\"What problem does the report address?\",\"answer\":\"It addresses learning semantic relations for SAT-style verbal analogy questions and for classifying noun-modifier pairs by the relation between the noun and modifier.\"},{\"question\":\"How does the proposed algorithm solve verbal analogy problems?\",\"answer\":\"It uses a Vector Space Model approach to identify the most analogous word pair C:D given a query pair A:B, then selects the best match among candidate choices.\"},{\"question\":\"What results does the report report for analogy and noun-modifier relation tasks?\",\"answer\":\"On 374 college-level analogy questions, the algorithm reaches 47% correct (vs 20% random). For noun-modifier relations, nearest-neighbour learning achieves F values of 26.5% with 30 classes and 43.2% with 5 classes, described as state-of-the-art for these settings.\"}]","Learning Analogies and Semantic Relations - Research report | PDF",71,{"code":4,"msg":82,"data":99},[100,104,108,112,117,122,127,130,135,138,142],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},5,"Comic",60,"comic",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},6,"Technology",50,"technology",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":125,"slug":126},7,"Healthcare",40,"healthcare",{"id":86,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":128,"slug":129},30,"research-report",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":133,"slug":134},9,"Religion & Spirituality",20,"religion-spirituality",{"id":133,"doc_module":4,"doc_module_name":25,"category_name":136,"show_sort_weight":133,"slug":137},"World Cup","world-cup",{"id":139,"doc_module":4,"doc_module_name":25,"category_name":140,"show_sort_weight":139,"slug":141},10,"Lifestyle","lifestyle",{"id":143,"doc_module":4,"doc_module_name":25,"category_name":144,"show_sort_weight":113,"slug":145},19,"General","general"]