{"id":12800,"date":"2022-10-27T09:04:33","date_gmt":"2022-10-27T13:04:33","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=12800"},"modified":"2022-10-27T09:04:33","modified_gmt":"2022-10-27T13:04:33","slug":"getting-tabular-data-from-unstructured-text-with-gpt-3-an-ongoing-experiment","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/getting-tabular-data-from-unstructured-text-with-gpt-3-an-ongoing-experiment\/12800\/","title":{"rendered":"Getting Tabular Data from Unstructured Text with GPT-3: An Ongoing Experiment"},"content":{"rendered":"Originally published by Roberto Rocha. One of the most exciting applications of AI in journalism is the creation of structured data from unstructured text. Government reports, legal documents, emails, memos\u2026 these are rich with content like names, organizations, dates, and prices. But to get them into a format that can be analyzed and counted, like a spreadsheet, usually involves days or weeks of tedious manual data entry. Large language models like\u00a0GPT-3 from OpenAI\u00a0have the potential to greatly speed up this awful slog. Because these models have such a deep grasp of language (GPT-3 was trained on basically the <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/getting-tabular-data-from-unstructured-text-with-gpt-3-an-ongoing-experiment\/12800\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published by Roberto Rocha. One of the most exciting applications of AI in journalism is the creation of structured data from unstructured text. Government reports, legal documents, emails, memos\u2026 these are rich with content like names, organizations, dates, and prices. But to get them into a format that can be analyzed and counted, like [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[879,368,791,1198,243,612,8],"class_list":["post-12800","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-ai","tag-artificial-intelligence","tag-deep-learning","tag-language-models","tag-machine-learning","tag-predictive-analysis","tag-predictive-analytics"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12800","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=12800"}],"version-history":[{"count":1,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12800\/revisions"}],"predecessor-version":[{"id":12801,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12800\/revisions\/12801"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=12800"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=12800"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=12800"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}