{"id":5624,"date":"2024-09-19T15:00:06","date_gmt":"2024-09-19T06:00:06","guid":{"rendered":"http:\/\/www-dsc.naist.jp\/dsc_naist\/?p=5624"},"modified":"2024-10-23T11:29:13","modified_gmt":"2024-10-23T02:29:13","slug":"dsc-internal-talk-in-september2024","status":"publish","type":"post","link":"http:\/\/www-dsc.naist.jp\/dsc_naist\/en\/dsc-internal-talk-in-september2024\/","title":{"rendered":"DSC internal talk in September"},"content":{"rendered":"<p>Asst. Prof. Akinori Sato gave a lecture in September.<\/p>\n<p>The details are as follows.<\/p>\n<p>====================<\/p>\n<p>Asst. Prof. Akinori Sato (Data-driven Chemistry Laboratory)<\/p>\n<p>TITLE:<br \/>\nData extraction with large language models(LLMs)<\/p>\n<p>ABSTRACT\uff1a<br \/>\nIn the field of Chemoinformatics, a large amount of data are preferable for building accurate prediction models. For some targets, data are ubiquitous in literature but are hardly organized to be applied for quantitative analyses. While manual data c<br \/>\nollection from scientific papers is possible, this process is cost demanding and not suitable for large-scale data collection.<br \/>\nThus, inspired by the rapid development of LLMs, several studies have begun to use LLMs to extract data from publicly accessible documents. In this talk, I will present progress on data extraction from scientific papers using LLMs.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<div class=\"block-list-appender wp-block\" tabindex=\"-1\" contenteditable=\"false\" data-block=\"true\">\n<div class=\"block-editor-default-block-appender\" data-root-client-id=\"\">\n<p class=\"block-editor-default-block-appender__content\" tabindex=\"0\" role=\"button\" aria-label=\"\u30c7\u30d5\u30a9\u30eb\u30c8\u30d6\u30ed\u30c3\u30af\u3092\u8ffd\u52a0\">\u00a0<\/p>\n<\/div>\n<\/div>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Asst. Prof. Akinori Sato gave a lecture in September. The details are as follows. ==================== Asst. Prof. Akinori Sato (Data-driven Chemistry Laboratory) TITLE: Data extraction with large language models(LLMs) ABSTRACT\uff1a In the field of Chemoinformatics, a large amount of data are preferable for building accurate prediction models. For some targets, data are ubiquitous in literature [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_locale":"en_US","_original_post":"http:\/\/www-dsc.naist.jp\/dsc_naist\/?p=5621","_links_to":"","_links_to_target":""},"categories":[3],"tags":[],"event_taxonomy":[15],"acf":[],"_links":{"self":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5624"}],"collection":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/comments?post=5624"}],"version-history":[{"count":2,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5624\/revisions"}],"predecessor-version":[{"id":5626,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/posts\/5624\/revisions\/5626"}],"wp:attachment":[{"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/media?parent=5624"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/categories?post=5624"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/tags?post=5624"},{"taxonomy":"event_taxonomy","embeddable":true,"href":"http:\/\/www-dsc.naist.jp\/dsc_naist\/wp-json\/wp\/v2\/event_taxonomy?post=5624"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}