[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-192491-105":53,"doc-detail-192491-en":126},{"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":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","cs224n-lecture-1-introduction-to-natural-language-processing","CS224N Lecture 1 - Introduction to Natural Language Processing","","Lecture 1 introduces foundational concepts behind natural language processing, explaining why natural language computing is difficult through real newspaper headline examples. It outlines early historical context from the 1950s, highlights core research areas such as automata, formal languages, probabilities, and information theory, and notes early speech and machine translation efforts. The lecture frames the problem as intractable while motivating modern progress via probabilistic models built from language data, alongside the need for language knowledge, world knowledge, and methods to combine them.",{"@graph":63,"@context":118},[64,80,101],{"@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/cs224n-lecture-1-introduction-to-natural-language-processing/192491/",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/cs224n-lecture-1-introduction-to-natural-language-processing/192491.png","ImageObject",442,249,{"name":88,"@type":89},"Clementine","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-09-28","2026-09-03",true,{"@type":98,"interactionType":99,"userInteractionCount":76},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What is the main reason natural language processing is difficult?","Question",{"text":108,"@type":109},"Natural language is highly ambiguous at all levels and relies on complex, subtle context. It also requires reasoning about the world and involves fuzzy, probabilistic interpretation.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"What tools does the lecture say NLP needs to make progress?",{"text":113,"@type":109},"It highlights the need for knowledge about language, knowledge about the world, and a way to combine knowledge sources. It then emphasizes probabilistic models built from language data as a major approach.",{"name":115,"@type":106,"acceptedAnswer":116},"How does the lecture use examples to explain NLP difficulty or progress?",{"text":117,"@type":109},"Newspaper headlines illustrate extreme ambiguity and contextual dependence, while translation examples compare human versus machine translation quality and show that interpreting and generating language are both required tasks.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},192491,1788416014,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":76,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"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":125,"read_time":76},1374391974564,"https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002","|  Natural language: the earliest UI\u003Cbr>Dave Bowman: Open the pod bay doors, HAL. HAL: I’m sorry Dave. I’m afraid I can’t do that.\u003Cbr>|  |\n| --- | --- |\n| | |\n| (cf. also false Maria in Metropolis – 1926) |  |\n\n|  The early history: 1950s\u003Cbr>|\n| --- |\n| \u003Cbr>• Early (Machine Translation) machines less powerful than pocket calculators\u003Cbr>• Foundational work on automata, formal languages, probabilities, and information theory\u003Cbr>• First speech systems (Davis et al. , Bell Labs)\u003Cbr>• MT heavily funded by military, but basically just word substitution programs\u003Cbr>• Little understanding of natural language syntax, semantics, pragmatics\u003Cbr>• Problem appeared intractable |\n\n| | Why NLP is difficult: Newspaper headlines |\n| --- | --- |\n| • Minister Accused Of Having 8 Wives In Jail\u003Cbr>• Juvenile Court to Try Shooting Defendant\u003Cbr>• Teacher Strikes Idle Kids\u003Cbr>• China to Orbit Human on Oct. 15\u003Cbr>• Local High School Dropouts Cut in Half\u003Cbr>• Red Tape Holds Up New Bridges\u003Cbr>• Clinton Wins on Budget, but More Lies Ahead\u003Cbr>• Hospitals Are Sued by 7 Foot Doctors\u003Cbr>• Police: Crack Found in Man's Buttocks\u003Cbr>|  |\n\n| | Why is natural language computing hard? |\n| --- | --- |\n| • Natural language is:\u003Cbr>• highly ambiguous at all levels\u003Cbr>• complex and subtle use of context to convey meaning\u003Cbr>• fuzzy, probabilistic\u003Cbr>• involves reasoning about the world\u003Cbr>• a key part of people interacting with other people (asocial system):\u003Cbr>• persuading, insulting and amusing them\u003Cbr>• But NLP can also be surprisingly easy sometimes:\u003Cbr>• rough text features can often do half the job |  |\n\n| | Making progress on this problem… |\n| --- | --- |\n| • The task is difficult! What tools do we need?\u003Cbr>• Knowledge about language\u003Cbr>• Knowledge about the world\u003Cbr>• A way to combine knowledge sources\u003Cbr>• The answer that’s been getting traction:\u003Cbr>• probabilistic models built from language data\u003Cbr>• P(“maison”→“house”) high\u003Cbr>• P(“L’avocat général”→“the general avocado”) low\u003Cbr>• Some computer scientists think this is a new“A. I.” idea\u003Cbr>• But really it’s an old idea that was stolen from the electrical engineers…. |  |\n\n| Translation (human and machine) |  |\n| --- | --- |\n| Ref\u003Cbr>: | According to the data provided today by the Ministry of Foreign\u003Cbr>Trade and Economic Cooperation, as of November this year, China has actually utilized 46.959 billion US dollars of foreign capital, including 40.007 billion US dollars of direct investment from foreign businessmen. |\n| IBM4:\u003Cbr>the Ministry of Foreign Trade and Economic Cooperation, including foreign direct investment 40.007 billion US dollars today provide data include\u003Cbr>that year to November china actually using foreign 46.959 billion US dollars and Yamada/Knight:\u003Cbr>today’s available data of the Ministry of Foreign Trade and Economic Cooperation shows that china’s actual utilization of November this year will include 40.007 billion US dollars for the foreign direct investment among 46.959 billion US dollars in foreign capital |  |\n\n| Machine Translation |  |  |\n| --- | --- | --- |\n| 美国关岛国际机场及其办公室均接获一名自称沙地阿拉伯富商拉登等发出的电子邮件，威胁将会向机场等公众地方发动生化袭击後，关岛经保持高度戒备。 | | The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport . |\n| The classic acid test for natural language processing. Requires capabilities in both interpretation and generation. About $10 billion spent annually on human translation.\u003Cbr>\u003Cbr>Scott Klemmer: I learned a surprising fact at our research group lunch today. Google Sketchup releases a version every 18 months, and the primary difficulty of releasing more often is not the difficulty of producing software, but the cost of internationalizing the user manuals!\u003Cbr>\u003Cbr>Mainly slides from Kevin Knight (at ISI) |  |  |\n\n\n| \u003Cbr>Called on organization Human Rights Watch the Israeli authorities to ","cbCaitkDJSGu2yHm","https://ap.wps.com/l/cbCaitkDJSGu2yHm","pdf",2491423,9,"English","# Early history\n## Why NLP is difficult: Newspaper headlines\n## Why is natural language computing hard?\n## Making progress on this problem…\n# Translation and machine translation examples\n# Speech recognition basics","[{\"question\":\"What is the main reason natural language processing is difficult?\",\"answer\":\"Natural language is highly ambiguous at all levels and relies on complex, subtle context. It also requires reasoning about the world and involves fuzzy, probabilistic interpretation.\"},{\"question\":\"What tools does the lecture say NLP needs to make progress?\",\"answer\":\"It highlights the need for knowledge about language, knowledge about the world, and a way to combine knowledge sources. It then emphasizes probabilistic models built from language data as a major approach.\"},{\"question\":\"How does the lecture use examples to explain NLP difficulty or progress?\",\"answer\":\"Newspaper headlines illustrate extreme ambiguity and contextual dependence, while translation examples compare human versus machine translation quality and show that interpreting and generating language are both required tasks.\"}]","CS224N Lecture 1 - Introduction to Natural Language Processing | PDF"]