[{"data":1,"prerenderedAt":358},["ShallowReactive",2],{"project-5244456":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":45,"post_text":46,"what":47,"said":88,"maker_in_thread":206,"shape":214,"grid":217,"attempts":319,"same_week":320,"maker_shows":39,"maker_hidden":350,"reader_version":351,"card":352},"5244456","TextRazor","A scriptable text mining API","title","Show HN: TextRazor, a scriptable text mining API","http:\u002F\u002Fwww.textrazor.com","textrazor.com","tcwc",1361284535,2013,118,44,185,1739,11,"notable","ai","text mining api","api",[24,25,26,27],"text mining","entity extraction","nlp api","topic extraction","mixed",0.265,{"positive":31,"neutral":32,"mixed":33,"critical":34},13,6,3,5,27,{"idea":37,"execution":40,"pricing":42,"performance":44},{"positive":38,"critical":39},8,1,{"positive":33,"critical":41},2,{"positive":43,"critical":41},0,{"positive":39,"critical":43},[34,39,43,43,43,39,43,33,34,39,43,43,33,43,43,43,43,39,43,34,33,34,34,34,34,43,43,33,33,34,33,39,34,43,33,34,34,33,43,34],null,{"problem":48,"audience":59,"pricing":72,"motivation":46,"time_to_build":46,"stack":81,"openness":86,"stage":87,"team_size":86},{"value":49,"source":50,"evidence":51},"Extracting structured entities and topics from unstructured text","maker",[52,55],{"id":53,"by":11,"text":54},"5245080","The Stanford parser is great, but isn't really the same. The Stanford entity recogniser is limited to the standard types of people, places, companies, but we identify and…",{"id":56,"by":57,"text":58},"5247035","JPKab","It's certainly not going to be ideal for your typical CRUD app. Think about all of the information that is locked inside of unstructured text (MS word docs, pdf's come to mind),…",{"value":60,"source":61,"evidence":62},"Developers building apps that process news, documents or user content","commenter",[63,64,68],{"id":56,"by":57,"text":58},{"id":65,"by":66,"text":67},"5247954","jsmcgd","Awesome stuff. It would be great to use something like this for suggesting relevant tags of content. Perhaps a WordPress or Drupal plugin to get the ball rolling.",{"id":69,"by":70,"text":71},"5251299","Mikushi","Extracting important keywords from thousands of pages for example. On our website we let user enter quite a lot of content, and being able to extract keywords and find patterns…",{"value":73,"source":50,"evidence":74},"Not yet decided; free plan promised",[75,78],{"id":76,"by":11,"text":77},"5245470","I can understand why you might think that, but we'll always have the free plan. We're still working out all the little pricing details.",{"id":79,"by":11,"text":80},"5245010","Hey steeve we thought there were a few things missing in the competition. We've built a bunch of extra functionality such as more extensive relation and dependency parsing and…",[82],{"value":83,"source":50,"evidence":84},"Prolog interpreter on backend",[85],{"id":79,"by":11,"text":80},"unknown","launched",{"praise":89,"objections":112,"requests":139,"questions":159,"alternatives":178},[90,105],{"value":91,"source":61,"evidence":92},"Entity and topic recognition results are impressive",[93,97,101],{"id":94,"by":95,"text":96},"5244725","abaer","Really impressive results. I put in some music reviews, and it did an excellent job of identifying artists, Genres, labels, etc. From an API perspective,there's not much out…",{"id":98,"by":99,"text":100},"5246396","movingahead","This is very impressive stuff. I ran a news article through the demo, and the entity recognition was very impressive. Waiting for them to reveal more details on pricing.",{"id":102,"by":103,"text":104},"5246662","PaulHoule","This is the best Wikipedia-backed namex I've seen and I've seen a lot of them, worked on code for one, and even designed one. Awesome!",{"value":106,"source":61,"evidence":107},"Customizable, scriptable results are a killer feature",[108],{"id":109,"by":110,"text":111},"5246128","adelevie","This looks great. I'm building http:\u002F\u002Fdokket.aws.af.cm. It's a database filled with documents from the Federal Communications Commission. From day 1, I've been looking for smart…",[113,132],{"value":114,"source":61,"evidence":115},"No pricing published",[116,120,124,128],{"id":117,"by":118,"text":119},"5244590","steeve","Cool demo, but how do you guys compare to, say, Alchemy API ? Also, no pricing => not cool.",{"id":121,"by":122,"text":123},"5244830","thejosh","No pricing at all on the website is fishy for anyone who wants to use the free plan?",{"id":125,"by":126,"text":127},"5247835","thehodge","I don't know if your just being slammed right now but I posted a request for pricing and haven't got anything.. it looks like a nice API to integrate into our system but it…",{"id":129,"by":130,"text":131},"5246056","beebs93","Wow, nice demo. I agree with the others the lack of pricing is a bit disconcerting. Btw, anyone else read the title as \"Trent Reznor\"? I need a coffee...",{"value":133,"source":61,"evidence":134},"Inconsistent results on some articles",[135],{"id":136,"by":137,"text":138},"5249265","richardofyork","I am also building an application that could use this service. So I tested TextRazor and the results were not good on two random articles I processed with the service. I really…",[140,145,152],{"value":141,"source":61,"evidence":142},"Publish clear pricing",[143,144],{"id":125,"by":126,"text":127},{"id":117,"by":118,"text":119},{"value":146,"source":61,"evidence":147},"Offline or packaged library option",[148],{"id":149,"by":150,"text":151},"5244846","habosa","Wow, this seems incredible, signed up immediately. My mind is already spinning with all of the cool apps I could make with this. How hard would it be to allow this functionality…",{"value":153,"source":61,"evidence":154},"Listing on Mashape",[155],{"id":156,"by":157,"text":158},"5248716","sinzone","Hi, would love to have this API listed on Mashape",[160,171],{"value":161,"source":61,"evidence":162},"How does it compare to Alchemy API and OpenCalais",[163,164,167],{"id":117,"by":118,"text":119},{"id":165,"by":57,"text":166},"5245212","How does your offering compare to Calais from Thomson-Reuters? Edit: To be specific, it looks very similar. What do you have that Calais doesn't?",{"id":168,"by":169,"text":170},"5246371","typpo","There are a number of other competing APIs. One of the best is OpenCalais, which is owned by Thomson Reuters[1]. You can demo it with some text here:…",{"value":172,"source":61,"evidence":173},"Sentiment analysis support",[174],{"id":175,"by":176,"text":177},"5249562","atrilla","Great work! But I missed the \"sentiment analysis\" flavour that used to be so popular some years ago with the NLP bunch... In this sense, I did something similar:…",[179,188,198,202],{"value":180,"source":61,"evidence":181},"OpenCalais",[182,183,184],{"id":165,"by":57,"text":166},{"id":168,"by":169,"text":170},{"id":185,"by":186,"text":187},"5245539","mark_l_watson","I have been using the free tier (50K API calls per day) of Open Calais for years and have also used it in code examples in three books I have written. One thing that Open Calais…",{"value":189,"source":61,"evidence":190},"Stanford parser and NLP tools",[191,195],{"id":192,"by":193,"text":194},"5244875","anilshanbhag","This is just like stanford parser. http:\u002F\u002Fnlp.stanford.edu:8080\u002Fparser\u002F Why use TextRazor and pay for it ?",{"id":196,"by":186,"text":197},"5244955","The Stanford NLP tools are very good, and also GPLed, which works for a lot of projects. If the GPL doesn't work for you, the Apache OpenNLP project is also good.",{"value":199,"source":61,"evidence":200},"Alchemy API",[201],{"id":117,"by":118,"text":119},{"value":203,"source":61,"evidence":204},"Apache OpenNLP",[205],{"id":196,"by":186,"text":197},{"comments":34,"answered":207,"key":208},4,[209,212,213],{"id":210,"text":211},"5251718","No tweaking, promise :) It's possible you hit an inconsistent server first time around, I'll have a dig on our end. Let me know if you have any other problems - toby@textrazor.com.",{"id":79,"text":80},{"id":53,"text":54},{"commenters":215,"max_depth":34,"maker_replies":34,"first_comment_mins":216,"lifespan_hours":35},30,26,[218,220,222,225,227,229,231,233,237,240,242,243,245,247,248,250,253,255,257,258,261,262,264,265,268,269,271,274,277,281,282,285,287,288,291,294,298,301,303,305,307,309,312,314],[109,43,34,219,110,43],"project\u002Fpositive\u002Fidea",[136,43,39,221,137,43],"project\u002Fcritical\u002Fexecution",[223,43,43,224,66,43],"5249873","commenter\u002Fneutral\u002Fnone",[226,43,43,224,137,43],"5251162",[210,43,43,228,11,39],"maker\u002Fneutral\u002Fexecution",[117,39,39,230,118,43],"project\u002Fcritical\u002Fpricing",[79,39,43,232,11,39],"maker\u002Fneutral\u002Fidea",[234,39,33,235,236,43],"5245264","maker\u002Fneutral\u002Fpricing","ismaelc",[238,39,34,239,103,43],"5246780","project\u002Fpositive\u002Fperformance",[192,41,39,241,193,43],"project\u002Fcritical\u002Fidea",[196,41,43,224,186,43],[244,41,43,224,186,43],"5245004",[53,41,43,246,11,39],"project\u002Fneutral\u002Fidea",[165,41,33,246,57,43],[185,41,43,249,186,43],"other\u002Fneutral\u002Fnone",[251,41,43,249,252,43],"5245202","gsharma",[254,41,43,224,186,43],"5245458",[256,41,43,224,252,43],"5245555",[121,33,39,230,122,43],[259,33,43,260,186,43],"5244947","other\u002Fneutral\u002Fpricing",[76,33,43,235,11,39],[94,207,34,263,95,43],"project\u002Fpositive\u002Fexecution",[168,207,33,246,169,43],[266,34,34,219,267,43],"5245218","polskibus",[98,32,34,263,99,43],[149,270,34,219,150,43],7,[272,38,34,219,273,43],"5245194","ses",[275,38,43,276,11,39],"5245486","maker\u002Fneutral\u002Fnone",[278,279,43,249,280,43],"5246933",9,"petercooper",[56,279,33,246,57,43],[283,279,33,246,284,43],"5247281","foobar2k",[286,279,34,219,110,43],"5248305",[69,279,33,246,70,43],[175,289,33,290,176,43],10,"project\u002Fmixed\u002Fidea",[292,18,39,221,293,43],"5244592","GotAnyMegadeth",[295,296,34,219,297,43],"5246293",12,"doktrin",[299,296,43,249,300,43],"5249453","wiradikusuma",[125,31,33,302,126,43],"project\u002Fmixed\u002Fpricing",[65,304,34,219,66,43],14,[102,306,34,263,103,43],15,[129,308,33,302,130,43],16,[310,308,43,249,311,43],"5246992","snake_plissken",[156,313,34,219,157,43],17,[315,316,34,317,318,43],"5246383",18,"project\u002Fpositive\u002Fnone","eurodance",[],[321,326,331,336,341,346],{"id":322,"name":323,"points":324,"category":325},"5238537","What colour is your IP address?",208,"other",{"id":327,"name":328,"points":329,"category":330},"5251361","importd",116,"languages",{"id":332,"name":333,"points":334,"category":335},"5231487","bcp",110,"dev_tools",{"id":337,"name":338,"points":339,"category":340},"5216992","Semantics3",108,"data",{"id":342,"name":343,"points":344,"category":345},"5231435","Docracy Mobile Privacy Policy",106,"learning_science",{"id":347,"name":348,"points":349,"category":335},"5237979","browser-details",93,false,"v2",{"id":353,"name":5,"line":6,"ai":350,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":354,"top":18,"kw":355,"maker":11,"domain":10,"tier":19,"attempts":43,"strip":356,"url":9,"mix":357,"praise":91,"objection":114,"sub":21},5244456,0.27,[24,25,26,27],"5100010351003000010535555003353150355305",[31,32,33,34],1793990891055]