{"id":125,"date":"2016-02-24T14:19:50","date_gmt":"2016-02-24T14:19:50","guid":{"rendered":"http:\/\/muthu.co\/?p=125"},"modified":"2021-01-02T14:06:04","modified_gmt":"2021-01-02T14:06:04","slug":"grus-an-intelligent-question-answering-machine","status":"publish","type":"post","link":"http:\/\/write.muthu.co\/grus-an-intelligent-question-answering-machine\/","title":{"rendered":"Grus – An intelligent question answering machine"},"content":{"rendered":"

Lets say I give you a print out of Professor Albert Einstein’s Wikipedia page<\/a>\u00a0and tell you that I am going to ask you questions from that text. You will have enough time to read through the document and find the answers that I am looking for. Assuming you are good at finding answers, here is what our conversation may look like.<\/p>\n

Me\u00a0- When did Albert Einstein win the Nobel prize for physics?\r\nYou - 1921\r\nMe - What was Einstein age when he died?\r\nYou - 76\r\nMe - How many children did Einstein have?\r\nYou - 3,\u00a0Eduard Einstein, Lieserl Einstein, Hans Albert Einstein\r\nMe - Which musical instrument did Einstein play?\r\nYou - Violin\r\nMe -\u00a0What did Einstein receive the Nobel prize for?\r\nYou -\u00a0for his services to Theoretical Physics, and especially for his discovery of the law of the photoelectric effect\r\n\r\n<\/pre>\n

For a human mind to do this task is fairly easy but\u00a0for a machine it takes a lot more than just feeding in the document and running a text search. This is what I am trying to build, an intelligent machine programmed to extract facts from documents and organize them in its\u00a0memory and provide answers to questions given in natural language. I call him Grus.<\/p>\n

How is it different from other search engines? Take a look at the below snapshot.<\/p>\n

\"google\"<\/a><\/p>\n

WolframAlpha had no clue what I am trying to find while Google was lucky to find the exact text match in one of the pages so was able to come back with the relevant links.<\/p>\n

Here is another example.<\/p>\n

\"google\"<\/a><\/p>\n

This time neither WolframAlpha nor Google could figure out what I am trying to ask. While its easy to go through the links and find the answer but is it worth the time? Why can’t I just have a one word answer\u00a0to my question?<\/p>\n

 <\/p>\n

Watch this space for more info on the progress of Grus (grus.io) – An intelligent question answering machine. <\/p>\n","protected":false},"excerpt":{"rendered":"

Lets say I give you a print out of Professor Albert Einstein’s Wikipedia page\u00a0and tell you that I am going to ask you questions from that text. You will have enough time to read through the document and find the answers that I am looking for. Assuming you are good at finding answers, here is […]<\/p>\n","protected":false},"author":1,"featured_media":128,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[19],"tags":[50,20,21],"_links":{"self":[{"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/posts\/125"}],"collection":[{"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/comments?post=125"}],"version-history":[{"count":1,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/posts\/125\/revisions"}],"predecessor-version":[{"id":1663,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/posts\/125\/revisions\/1663"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/media\/128"}],"wp:attachment":[{"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/media?parent=125"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/categories?post=125"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/write.muthu.co\/wp-json\/wp\/v2\/tags?post=125"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}