[{"data":1,"prerenderedAt":253},["ShallowReactive",2],{"project-7090117":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":34,"aspects":35,"strip":42,"post_text":44,"what":45,"said":67,"maker_in_thread":158,"shape":168,"grid":172,"attempts":213,"same_week":214,"maker_shows":32,"maker_hidden":245,"reader_version":246,"card":247},"7090117","Akiva","A simple NLP, question-answering artificial intelligence","title","Show HN: Akiva – A simple NLP, question-answering artificial intelligence","https:\u002F\u002Fgithub.com\u002Fthebigdb\u002Fakiva","github.com","christophe971",1390233653,2014,71,20,427,2272,19,"notable","ai","question answering","cli",[21,24,25,26,27],"nlp","knowledge base","thebigdb","natural language","mixed",-0.038,{"positive":31,"neutral":32,"mixed":33,"critical":33},2,4,3,12,{"idea":36,"docs":39,"design":40,"performance":41},{"positive":37,"critical":38},1,0,{"positive":38,"critical":38},{"positive":38,"critical":38},{"positive":38,"critical":33},[33,38,33,38,33,43,38,33,38,33,37,37,38,38,38,43,38,33,33,37],5,null,{"problem":46,"audience":44,"pricing":44,"motivation":44,"time_to_build":44,"stack":56,"openness":64,"stage":65,"team_size":66},{"value":47,"source":48,"evidence":49},"Answering natural language questions from a fact database","inferred",[50,52],{"id":51},"post",{"id":53,"by":54,"text":55},"7090464","nnx","It's a very MVP simple implementation that works well for most cases. Kudos. That said, looking at the code, I'm not sure why you call it an AI when it is very rule-based so the…",[57],{"value":58,"source":59,"evidence":60},"TheBigDB","maker",[61],{"id":62,"by":11,"text":63},"7090514","Everything you said is very much correct. On the \"AI\" title, I know there is a long debate about what constitutes an AI and what doesn't, and I'm sure you're also aware of it, so…","open_source","prototype","unknown",{"praise":68,"objections":78,"requests":115,"questions":132,"alternatives":141},[69],{"value":70,"source":71,"evidence":72},"Works well for the example questions and is a nice MVP","commenter",[73,74],{"id":53,"by":54,"text":55},{"id":75,"by":76,"text":77},"7090802","pmelendez","I like the idea, but unfortunately I only got results with the example questions. For instance: > akiva ask \"What's the weight of an iPhone 5s ?\" 112 grams is fine, but: > akiva…",[79,96,104],{"value":80,"source":71,"evidence":81},"Database is nearly empty, so most questions go unanswered",[82,83,84,88,92],{"id":53,"by":54,"text":55},{"id":75,"by":76,"text":77},{"id":85,"by":86,"text":87},"7090821","bromagosa","Same here... I tried really different kinds of questions and couldn't get an answer. ``` $ akiva ask \"Is the empire states building higher than the eiffel tower ?\" Sorry, Akiva…",{"id":89,"by":90,"text":91},"7091430","casualobs","this is interesting, but none of the questions i've asked seem to get answered, even after wording them well and picking easy questions..like 20 questions in a row",{"id":93,"by":94,"text":95},"7092537","silentrob","This looks amazing, and I agree, you need to bootstrap theBigDB with more facts. Sources like freebase and perhaps DBPedia would help. It would also be cool to layer on temporal…",{"value":97,"source":71,"evidence":98},"Called AI but it is rule-based",[99,100],{"id":53,"by":54,"text":55},{"id":101,"by":102,"text":103},"7090793","tylerkahn","As best I can tell this is more like an English-looking CFG with a simple attribute grammar. And the rules can be updated at runtime.",{"value":105,"source":71,"evidence":106},"Should use an existing knowledge base like Freebase instead of TheBigDB",[107,111],{"id":108,"by":109,"text":110},"7090733","TeeWEE","Why don't you use an existing ontology\u002Fknowledge graph instead of building your own with thebigdb? For example: http:\u002F\u002Fwww.freebase.com\u002F",{"id":112,"by":113,"text":114},"7091516","hcarvalhoalves","Your project sounds awesome, the NLP part seems to be working nicely, but I'm afraid it depends on the quality of the data source, which right now is empty (I only saw some facts…",[116,125],{"value":117,"source":71,"evidence":118},"Populate TheBigDB from Freebase or DBpedia",[119,123,124],{"id":120,"by":121,"text":122},"7090643","kybernetikos","have you considered integrating with freebase or perhaps populating theBigDB from freebase? http:\u002F\u002Fwww.freebase.com\u002F",{"id":93,"by":94,"text":95},{"id":112,"by":113,"text":114},{"value":126,"source":71,"evidence":127},"Add speech recognition",[128],{"id":129,"by":130,"text":131},"7090332","oelmekki","Very nice. I wonder, do you plan to couple this with any kind of speech recognition at any point, so we could have some kind of custom siri ?",[133,137],{"value":134,"source":71,"evidence":135},"Why call it AI when it is rule-based",[136],{"id":53,"by":54,"text":55},{"value":138,"source":71,"evidence":139},"Why not use an existing ontology like Freebase",[140],{"id":108,"by":109,"text":110},[142,147,151],{"value":143,"source":71,"evidence":144},"Freebase",[145,146],{"id":120,"by":121,"text":122},{"id":108,"by":109,"text":110},{"value":148,"source":71,"evidence":149},"DBpedia",[150],{"id":93,"by":94,"text":95},{"value":152,"source":71,"evidence":153},"MegaHAL",[154],{"id":155,"by":156,"text":157},"7091355","aluhut","I wish there would be a cleaner V2 version of megahal out there. I loved that thing but the last time I've implemented it into eggdrop (which is hopelessly outdated too) I was…",{"comments":159,"answered":43,"key":160},6,[161,162,165],{"id":62,"text":63},{"id":163,"text":164},"7090736","I'm not sure what's the licensing of what's in Freebase but I'll look into it, thanks!",{"id":166,"text":167},"7091318","haha, thank you :) Strange indeed...",{"commenters":169,"max_depth":43,"maker_replies":159,"first_comment_mins":170,"lifespan_hours":171},14,36,8,[173,175,177,179,180,184,188,189,191,193,195,197,198,201,203,205,207,209,210,212],[53,38,33,174,54,38],"project\u002Fmixed\u002Fidea",[62,38,38,176,11,37],"maker\u002Fneutral\u002Fnone",[120,38,33,178,121,38],"project\u002Fneutral\u002Fdocs",[163,38,38,176,11,37],[181,38,33,182,183,38],"7091590","project\u002Fneutral\u002Fnone","cocoflunchy",[185,37,43,186,187,38],"7091198","maker\u002Fpositive\u002Fnone","sinkasapa",[166,37,38,176,11,37],[108,31,33,190,109,38],"project\u002Fneutral\u002Fdesign",[192,31,38,190,11,37],"7090767",[112,31,33,194,113,38],"project\u002Fmixed\u002Fperformance",[75,33,37,196,76,38],"project\u002Fcritical\u002Fperformance",[85,33,37,196,86,38],[199,33,38,200,11,37],"7090832","commenter\u002Fneutral\u002Fnone",[202,33,38,200,86,38],"7090896",[155,32,38,204,156,38],"other\u002Fneutral\u002Fnone",[129,43,43,206,130,38],"project\u002Fpositive\u002Fidea",[208,43,38,176,11,37],"7090359",[93,159,33,194,94,38],[101,211,33,190,102,38],7,[89,171,37,196,90,38],[],[215,220,225,230,235,240],{"id":216,"name":217,"points":218,"category":219},"7095228","Geocodio",224,"data",{"id":221,"name":222,"points":223,"category":224},"7087927","hike.io",145,"consumer_social",{"id":226,"name":227,"points":228,"category":229},"7068672","Open-Source Data Science Curriculum",135,"learning_science",{"id":231,"name":232,"points":233,"category":234},"7094465","node-webkit-hipster-seed",101,"dev_tools",{"id":236,"name":237,"points":238,"category":239},"7090003","play-clj",93,"languages",{"id":241,"name":242,"points":243,"category":244},"7101923","Lychee",92,"infrastructure",false,"v2",{"id":248,"name":5,"line":6,"ai":245,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":249,"top":18,"kw":250,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":251,"url":9,"mix":252,"praise":70,"objection":80,"sub":21},7090117,-0.04,[21,24,25,26,27],"30303503031100050331",[31,32,33,33],1793990902147]