{"id":1208,"date":"2018-04-06T12:58:05","date_gmt":"2018-04-06T17:58:05","guid":{"rendered":"http:\/\/haleyai.com\/wordpress\/?p=1208"},"modified":"2018-07-13T18:27:55","modified_gmt":"2018-07-13T23:27:55","slug":"problems-with-probabilistic-parsing","status":"publish","type":"post","link":"http:\/\/haleyai.com\/wordpress\/2018\/04\/06\/problems-with-probabilistic-parsing\/","title":{"rendered":"Problems with Probabilistic Parsing"},"content":{"rendered":"<p>We are using statistical techniques to increase the automation of logical and semantic disambiguation, but nothing is easy with natural language.<\/p>\n<p>Here is the Stanford Parser (the probabilistic context-free grammar version) applied to a couple of sentences.\u00a0 <span style=\"text-decoration: underline;\">There is nothing wrong with the Stanford Parser<\/span>!\u00a0 It&#8217;s state of the art and worthy of respect for what it does well.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/Stanford-parse-tree-regulations.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-1209\" title=\"Stanford parse tree regulations\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/Stanford-parse-tree-regulations.png\" alt=\"\" width=\"1749\" height=\"857\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/Stanford-parse-tree-regulations.png 1749w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/Stanford-parse-tree-regulations-300x146.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/Stanford-parse-tree-regulations-1024x501.png 1024w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p><!--more-->It just goes to show you how far NLP is from understanding.<\/p>\n<p><a href=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/WSJhiringUnemploymentLabor.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-1219\" title=\"WSJhiringUnemploymentLabor\" src=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/WSJhiringUnemploymentLabor.png\" alt=\"\" width=\"1413\" height=\"874\" srcset=\"http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/WSJhiringUnemploymentLabor.png 1413w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/WSJhiringUnemploymentLabor-300x185.png 300w, http:\/\/haleyai.com\/wordpress\/wp-content\/uploads\/WSJhiringUnemploymentLabor-1024x633.png 1024w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><\/a><\/p>\n<p>Our software can&#8217;t get the right results without some help some of the time either.\u00a0 Nobody&#8217;s can.<\/p>\n<p>That&#8217;s why a cognitive computing approach is needed when accuracy is imperative.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We are using statistical techniques to increase the automation of logical and semantic disambiguation, but nothing is easy with natural language. Here is the Stanford Parser (the probabilistic context-free grammar version) applied to a couple of sentences.\u00a0 There is nothing wrong with the Stanford Parser!\u00a0 It&#8217;s state of the art and worthy of respect for &hellip; <\/p>\n<p class=\"link-more\"><a href=\"http:\/\/haleyai.com\/wordpress\/2018\/04\/06\/problems-with-probabilistic-parsing\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Problems with Probabilistic Parsing&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[214,782,864,863],"class_list":["post-1208","post","type-post","status-publish","format-standard","hentry","category-natural-language","tag-nlp","tag-parse-tree","tag-pcfg","tag-stanford-parser"],"_links":{"self":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/1208","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/comments?post=1208"}],"version-history":[{"count":12,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/1208\/revisions"}],"predecessor-version":[{"id":1217,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/1208\/revisions\/1217"}],"wp:attachment":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/media?parent=1208"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/categories?post=1208"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/tags?post=1208"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}