{"id":137,"date":"2021-01-19T10:29:26","date_gmt":"2021-01-19T10:29:26","guid":{"rendered":"https:\/\/multisite.korebots.com\/SearchAssist\/?p=137"},"modified":"2021-06-28T07:45:41","modified_gmt":"2021-06-28T07:45:41","slug":"semantic-meaning","status":"publish","type":"post","link":"https:\/\/multisite.korebots.com\/SearchAssist\/manage-index\/semantic-meaning\/","title":{"rendered":"Semantic Meaning"},"content":{"rendered":"<section class=\"l-section wpb_row height_auto\"><div class=\"l-section-h i-cf\"><div class=\"g-cols vc_row via_grid cols_1 laptops-cols_inherit tablets-cols_inherit mobiles-cols_1 valign_top type_default stacking_default\"><div class=\"wpb_column vc_column_container\"><div class=\"vc_column-inner\"><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><p><span style=\"font-weight: 400;\">Semantic analysis is the technique to understand the meaning and interpretation of words, signs, and sentence structure. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">SearchAssist&#8217;s <a href=\"\/SearchAssist\/lifecycle\/manage-index\/workbench\/\" target=\"_blank\" rel=\"noopener noreferrer\">Index pipeline<\/a> supports a Semantic Meaning stage. This stage uses <\/span><i><span style=\"font-weight: 400;\">Deep Neural Network<\/span><\/i><span style=\"font-weight: 400;\"> algorithms to create embeddings of free text and saves them in a dense vector field. These embeddings are used to rank the documents by semantic relevance. The dense vectors are then indexed in the ElasticSearch and similarity is obtained between the user\u2019s query vector and the indexed content vector.<\/span><\/p>\n<\/div><\/div><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><p>You can:<\/p>\n<ul>\n<li>Add multiple semantics to be analyzed from the source field.<\/li>\n<li>Define a condition for the semantic meaning stage. The semantics from only the documents that satisfy the given condition would be analyzed.<\/li>\n<li>Re-order or delete semantic meaning rules.<\/li>\n<li>Simulate the changes before saving them.<\/li>\n<\/ul>\n<div class=\"wpb_text_column \">\n<div class=\"wpb_wrapper\">\n<div class=\"wpb_text_column \">\n<div class=\"wpb_wrapper\">\n<p>Ensure to <strong>Train your app<\/strong> each time you make changes to any index configuration. This builds the index based on the updated configurations.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div><\/div><div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><h2><span class=\"ez-toc-section\" id=\"Configuration\"><\/span>Configuration<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">To configure semantic meaning, follow the below steps:<\/span><\/p>\n<ol>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Click the <\/span><b>Indices <\/b><span style=\"font-weight: 400;\">tab on the top.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">On the left pane, under the <\/span><b>Index Configuration<\/b><span style=\"font-weight: 400;\"> section, click <\/span><b>Workbench<\/b><span style=\"font-weight: 400;\">.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">On the Workbench (Index Configuration) page, on the <\/span><b>Stages <\/b><span style=\"font-weight: 400;\">column, click the <\/span><b>+<\/b><span style=\"font-weight: 400;\"> icon.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">On the right column, select <\/span><b>Semantic Meaning<\/b><span style=\"font-weight: 400;\"> from the <\/span><b>Stage Type<\/b><span style=\"font-weight: 400;\"> drop-down list.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Enter a name in the <\/span><b>Stage Name<\/b><span style=\"font-weight: 400;\"> field.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Enter a condition in the <\/span><b>Condition <\/b><span style=\"font-weight: 400;\">field. You can add multiple conditions using the AND\/OR connectors. Documents that satisfy the condition will be executed as part of the stage. <a href=\"#Conditions\">See below for details<\/a>.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Select the field you want to extract Semantic Meaning from as <\/span><b>Source Field<\/b>.<\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Define where you want to store the extracted Semantic Meaning as <\/span><b>Target Field<\/b>. This field is created by the application<span style=\"font-weight: 400;\">.<\/span><\/li>\n<li style=\"font-weight: 400;\">Choose a model from the\u00a0<b>Choose Model<\/b>\u00a0drop-down list.\u00a0<a href=\"#Models\">See below for details<\/a>.<\/li>\n<li>Click\u00a0<b>Simulate<\/b> to verify the configurations. The simulator displays the Source and the number of documents to which the mapping was applied, and the result. You can change the Source (if not mentioned in the condition) and the number of documents.<\/li>\n<li>Once done, click\u00a0<b>Save Configuration<\/b>\u00a0on the top-right.<\/li>\n<\/ol>\n<\/div><\/div><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><p><a ref=\"magnificPopup\" href=\"http:\/\/docs.kore.ai\/searchassist\/wp-content\/uploads\/sites\/4\/2021\/01\/indices_semantic.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-1275\" src=\"http:\/\/docs.kore.ai\/searchassist\/wp-content\/uploads\/sites\/4\/2021\/01\/indices_semantic.png\" alt=\"\" width=\"1119\" height=\"709\" \/><\/a><\/p>\n<\/div><\/div><div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><h3><span class=\"ez-toc-section\" id=\"Models\"><\/span><span id=\"Models\" class=\"ez-toc-section\"><span id=\"Actions\" class=\"ez-toc-section\">Models<\/span><\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>The following models are supported:<\/p>\n<ul>\n<li><strong>Universal Sentence Encoder<\/strong> &#8211; It encodes text into high-dimensional vectors that are used for semantic similarity.<\/li>\n<li><strong>Sentence Transformers<\/strong> &#8211; It is a framework for sentence and text embeddings.<\/li>\n<li><strong>InferSent<\/strong> &#8211; It is a sentence embedding method that provides semantic sentence representations.<\/li>\n<\/ul>\n<\/div><\/div><div class=\"wpb_text_column\"><div class=\"wpb_wrapper\"><h3><span class=\"ez-toc-section\" id=\"Conditions\"><\/span><span id=\"Conditions\" class=\"ez-toc-section\">Conditions<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Condition is of the following format:\u00a0<code>ctx.fieldtype==value<\/code>\u00a0or\u00a0<code>ctx.fieldtype!=value<\/code>. The\u00a0<em>field_name<\/em>\u00a0can be obtained from the Fields table under Index Configuration.<\/p>\n<p>For example,\u00a0<code>ctx.contentType==\"web\"<\/code>\u00a0to restrict the extraction to the content from a web source.<\/p>\n<\/div><\/div><div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div>[vc_raw_html]JTNDZGl2JTIwY2xhc3MlM0QlMjJ3LXBvc3QtZWxtJTIwcG9zdF9uYXZpZ2F0aW9uJTIwbGF5b3V0X3NpbXBsZSUyMGludl9mYWxzZSUyMiUzRSUwQSUwOSUzQ2ElMjBjbGFzcyUzRCUyMnBvc3RfbmF2aWdhdGlvbi1pdGVtJTIwb3JkZXJfZmlyc3QlMjB0b19wcmV2JTIyJTIwaHJlZiUzRCUyMiUyRlNlYXJjaEFzc2lzdCUyRm1hbmFnZS1pbmRleCUyRmVudGl0eS1leHRyYWN0aW9uJTJGJTIyJTNFJTNDJTJGcCUzRSUwQSUzQ2RpdiUyMGNsYXNzJTNEJTIycG9zdF9uYXZpZ2F0aW9uLWl0ZW0tYXJyb3clMjIlM0UlM0MlMkZkaXYlM0UlMEElM0NkaXYlMjBjbGFzcyUzRCUyMnBvc3RfbmF2aWdhdGlvbi1pdGVtLW1ldGElMjIlM0VQcmV2aW91cyUzQyUyRmRpdiUzRSUwQSUzQ2RpdiUyMGNsYXNzJTNEJTIycG9zdF9uYXZpZ2F0aW9uLWl0ZW0tdGl0bGUlMjIlM0UlM0NzcGFuJTNFRW50aXR5JTIwRXh0cmFjdGlvbiUzQyUyRnNwYW4lM0UlM0MlMkZkaXYlM0UlMEElM0NwJTNFJTNDJTJGYSUzRSUzQ2JyJTIwJTJGJTNFJTBBJTNDYSUyMGNsYXNzJTNEJTIycG9zdF9uYXZpZ2F0aW9uLWl0ZW0lMjBvcmRlcl9zZWNvbmQlMjB0b19uZXh0JTIyJTIwaHJlZiUzRCUyMiUyRlNlYXJjaEFzc2lzdCUyRm1hbmFnZS1pbmRleCUyRmN1c3RvbS1zY3JpcHQlMkYlMjIlM0UlM0MlMkZwJTNFJTBBJTNDZGl2JTIwY2xhc3MlM0QlMjJwb3N0X25hdmlnYXRpb24taXRlbS1hcnJvdyUyMiUzRSUzQyUyRmRpdiUzRSUwQSUzQ2RpdiUyMGNsYXNzJTNEJTIycG9zdF9uYXZpZ2F0aW9uLWl0ZW0tbWV0YSUyMiUzRU5leHQlM0MlMkZkaXYlM0UlMEElM0NkaXYlMjBjbGFzcyUzRCUyMnBvc3RfbmF2aWdhdGlvbi1pdGVtLXRpdGxlJTIyJTNFJTNDc3BhbiUzRUN1c3RvbSUyMFNjcmlwdCUzQyUyRnNwYW4lM0UlM0MlMkZkaXYlM0UlMEElM0NwJTNFJTNDJTJGYSUzRSUzQyUyRmRpdiUzRQ==[\/vc_raw_html]<div class=\"w-separator size_small with_line width_default thick_1 style_solid color_border align_center\"><div class=\"w-separator-h\"><\/div><\/div><\/div><\/div><\/div><\/div><\/section>\n","protected":false},"excerpt":{"rendered":"Semantic analysis is the technique to understand the meaning and interpretation of words, signs, and sentence structure. SearchAssist&#8217;s Index pipeline supports a Semantic Meaning stage. This stage uses Deep Neural Network algorithms to create embeddings of free text and saves them in a dense vector field. These embeddings are used to rank the documents by...","protected":false},"author":12,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/137"}],"collection":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/users\/12"}],"replies":[{"embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/comments?post=137"}],"version-history":[{"count":13,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/137\/revisions"}],"predecessor-version":[{"id":1222,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/137\/revisions\/1222"}],"wp:attachment":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/media?parent=137"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/categories?post=137"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/tags?post=137"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}