[{"data":1,"prerenderedAt":336},["ShallowReactive",2],{"project-33815146":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":9,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":45,"post_text":47,"what":48,"said":103,"maker_in_thread":177,"shape":189,"grid":192,"attempts":297,"same_week":298,"maker_shows":34,"maker_hidden":327,"reader_version":328,"card":329},"33815146","NLP Demystified","Natural Language Processing Demystified","title","Show HN: Natural Language Processing Demystified",null,"mothcamp",1669896001,2022,286,37,150,2570,6,"legend","learning_science","online course","web_app",[23,24,25,26,27],"natural language processing","nlp course","transformers","spacy","colab notebooks","loved",0.467,{"positive":31,"neutral":32,"mixed":33,"critical":34},14,4,0,2,20,{"docs":37,"execution":39,"privacy":41,"idea":42,"design":43,"pricing":44},{"positive":38,"critical":34},1,{"positive":40,"critical":33},5,{"positive":38,"critical":33},{"positive":34,"critical":33},{"positive":38,"critical":33},{"positive":33,"critical":33},[33,33,33,33,33,33,33,40,33,40,33,40,33,33,40,46,40,46,33,38,46,33,40,40,33,40,40,40,40,33,40,40,38,40,46,33,33,33],3,"Link: https:\u002F\u002Fwww.nlpdemystified.org\u002F\n\nHi HN:\n\nAfter a year of work, I've published my free NLP course. The course helps anyone who knows Python and a bit of math go from the basics to today's mainstream models and frameworks.\n\nI strive to balance theory and practice, so every module consists of detailed explanations and slides along with a Colab notebook putting the ideas into practice (in most modules).\n\nThe notebooks cover how to accomplish everyday NLP tasks including extracting key information, document search, text similarity, text classification, finding topics in documents, summarizati",{"problem":49,"audience":55,"pricing":62,"motivation":9,"time_to_build":69,"stack":73,"openness":100,"stage":101,"team_size":102},{"value":50,"source":51,"evidence":52},"Learning NLP from basics to modern transformer models with theory and practice.","maker",[53],{"id":54},"post",{"value":56,"source":51,"evidence":57},"Anyone who knows Python and a bit of math, per the maker.",[58,59],{"id":54},{"id":60,"by":10,"text":61},"33820066","It's for anyone who wants to learn NLP such that they get (a) an understanding of what's going on under the hood and (b) knowledge of how to get stuff done. So the ideal outcome…",{"value":63,"source":51,"evidence":64},"Free, no registration required.",[65,66],{"id":54},{"id":67,"by":10,"text":68},"33816864","Your time. That's it.",{"value":70,"source":51,"evidence":71},"After a year of work.",[72],{"id":54},[74,78,82,86,90,96],{"value":75,"source":51,"evidence":76},"Python",[77],{"id":54},{"value":79,"source":51,"evidence":80},"spaCy",[81],{"id":54},{"value":83,"source":51,"evidence":84},"scikit-learn",[85],{"id":54},{"value":87,"source":51,"evidence":88},"Google Colab notebooks",[89],{"id":54},{"value":91,"source":51,"evidence":92},"NextJS",[93],{"id":94,"by":10,"text":95},"33829174","Thanks. It's all statically-generated pages with NextJS and Tailwind.",{"value":97,"source":51,"evidence":98},"Tailwind",[99],{"id":94,"by":10,"text":95},"free","launched","solo",{"praise":104,"objections":138,"requests":153,"questions":161,"alternatives":176},[105,113,128],{"value":106,"source":107,"evidence":108},"Comprehensive and technical without getting lost in details.","commenter",[109],{"id":110,"by":111,"text":112},"33816479","reichardt","I love your course for being very comprehensive and technical while not getting lost in mundane details. Like the opposite of the following quote: “I didn't have time to write a…",{"value":114,"source":107,"evidence":115},"Free with no signup required.",[116,120,124],{"id":117,"by":118,"text":119},"33817552","insane_dreamer","10\u002F10 for making this freely available",{"id":121,"by":122,"text":123},"33817253","wazoox","This looks awesome. No signup, that's a dream :)",{"id":125,"by":126,"text":127},"33819577","account-5","I like that your site runs properly with only first party scripts enabled in ublock, very rare these days. Secondly kudos for not requiring a sign up and for making it free!…",{"value":129,"source":107,"evidence":130},"Clean, well-made video and audio.",[131,134],{"id":132,"by":111,"text":133},"33830976","That's impressive. The audio track of your videos is so clean and well understandable that I was wondering if you used a studio setup or voice synthesis software. Well done!",{"id":135,"by":136,"text":137},"33818119","yannis","Thanks excellent course, watched about an hour or two. Very well made. Deserves more exposure.",[139,146],{"value":140,"source":107,"evidence":141},"Wants written notes alongside the videos.",[142],{"id":143,"by":144,"text":145},"33817243","yupis","I wish there where written notes to study. Anyways great video.",{"value":147,"source":107,"evidence":148},"Notes that the tf-idf log10 explanation is misleading.",[149],{"id":150,"by":151,"text":152},"33828404","escanor","great work! just a note regarding tf-idf, when you mention log10: i think you're missing the point on the reason of log and most importantly base 10. namely, using log10 gives us…",[154],{"value":155,"source":107,"evidence":156},"Add a license to the GitHub repo.",[157],{"id":158,"by":159,"text":160},"33819994","santiagobasulto","Great content! And thank you for making it open and free. I recommend adding a License to your Github repo.",[162,169],{"value":163,"source":107,"evidence":164},"Who is the intended audience: app developers or ML developers?",[165],{"id":166,"by":167,"text":168},"33819785","posharma","Who is the intended audience for this course? Is it application developers looking to use NLP in their apps? Or machine\u002Fdeep learning devs?",{"value":170,"source":107,"evidence":171},"How to build one model that does multiple NLP tasks like NER and sentiment.",[172],{"id":173,"by":174,"text":175},"33817279","brooksbp","Thank you for sharing this! I am currently studying NLP.. Along the way, I've been struggling with a question and I hope someone can help me understand how to go about this: how…",[],{"comments":178,"answered":17,"key":179},7,[180,183,186],{"id":181,"text":182},"33817557","You could start by looking into either multitask transformers or really general seq2seq models like T5. With T5, for example, it just learns to transform one text sequence into…",{"id":184,"text":185},"33818139","Yeah, I can see that being the case for specialized domains. With state-of-the-art models widely available to the public, knowledge of the domain and its workflows, and…",{"id":187,"text":188},"33816610","Really appreciate that. Finding that balance was one of the hardest parts of building this course.",{"commenters":190,"max_depth":40,"maker_replies":178,"first_comment_mins":191,"lifespan_hours":190},27,92,[193,195,197,199,200,203,206,209,211,213,216,218,220,223,225,227,231,234,236,239,241,244,246,248,253,255,257,262,267,269,272,276,280,282,284,289,291,294],[173,33,33,194,174,33],"other\u002Fneutral\u002Fnone",[181,33,33,196,10,38],"commenter\u002Fneutral\u002Fnone",[198,33,33,196,174,33],"33817942",[184,33,33,194,10,38],[201,33,33,194,202,33],"33820036","trenchgun",[204,33,33,196,205,33],"33820627","axiom92",[207,33,33,194,208,33],"33820856","gattilorenz",[110,38,40,210,111,33],"project\u002Fpositive\u002Fdocs",[187,38,33,212,10,38],"maker\u002Fneutral\u002Fnone",[214,38,40,215,111,33],"33817615","project\u002Fpositive\u002Fexecution",[217,38,33,212,10,38],"33817685",[132,38,40,219,111,33],"maker\u002Fpositive\u002Fexecution",[221,38,33,194,222,33],"33819175","mharig",[224,38,33,194,111,33],"33819466",[125,34,40,226,126,33],"project\u002Fpositive\u002Fprivacy",[228,46,46,229,230,33],"33815973","project\u002Fneutral\u002Fnone","culanuchachamim",[232,32,40,215,233,33],"33825358","benjismith",[158,40,46,235,159,33],"project\u002Fneutral\u002Fdocs",[237,17,33,194,238,33],"33820144","fuzzythinker",[150,178,38,240,151,33],"project\u002Fcritical\u002Fdocs",[166,242,46,243,167,33],8,"project\u002Fneutral\u002Fidea",[60,242,33,245,10,38],"maker\u002Fneutral\u002Fidea",[247,242,40,215,167,33],"33821184",[249,250,40,251,252,33],"33827604",9,"maker\u002Fpositive\u002Fdesign","phodo",[94,250,33,254,10,38],"maker\u002Fneutral\u002Fdesign",[135,256,40,215,136,33],10,[258,259,40,260,261,33],"33817303",11,"project\u002Fpositive\u002Fidea","strumyktomira",[263,264,40,265,266,33],"33816112",12,"project\u002Fpositive\u002Fnone","jumasheff",[117,268,40,265,118,33],13,[270,31,33,194,271,33],"33821657","toolslive",[273,274,40,260,275,33],"33819355",15,"echobear",[277,278,40,265,279,33],"33819305",16,"clueless",[143,281,38,240,144,33],17,[121,283,40,265,122,33],18,[285,286,46,287,288,33],"33816824",19,"project\u002Fneutral\u002Fpricing","ddtaylor",[67,286,33,290,10,38],"maker\u002Fneutral\u002Fpricing",[292,35,33,194,293,33],"33817866","carvking",[295,35,33,194,296,33],"33819360","dang",[],[299,303,308,313,317,322],{"id":300,"name":301,"points":302,"category":19},"33833836","SQL for Devs",865,{"id":304,"name":305,"points":306,"category":307},"33853773","chat-gpt-google-extension",431,"dev_tools",{"id":309,"name":310,"points":311,"category":312},"33877893","Whisper",399,"ai",{"id":314,"name":315,"points":316,"category":312},"33882497","SmartyNames",313,{"id":318,"name":319,"points":320,"category":321},"33842406","Wikiwho",261,"data",{"id":323,"name":324,"points":325,"category":326},"33845946","This Hacker News Does Not Exist",252,"creative",false,"v2",{"id":330,"name":5,"line":6,"ai":327,"cat":19,"year":12,"points":13,"comments":14,"rec":28,"s":331,"top":17,"kw":332,"maker":10,"domain":333,"tier":18,"attempts":33,"strip":334,"url":-1,"mix":335,"praise":106,"objection":140,"sub":20},33815146,0.47,[23,24,25,26,27],"","00000005050500535301305505555055153000",[31,32,33,34],1794036627979]