{"id":1642,"date":"2022-01-09T11:22:09","date_gmt":"2022-01-09T11:22:09","guid":{"rendered":"https:\/\/multisite.korebots.com\/SearchAssist\/?p=1642"},"modified":"2022-01-18T06:03:56","modified_gmt":"2022-01-18T06:03:56","slug":"how-to-apply-semantic-meanings","status":"publish","type":"post","link":"https:\/\/multisite.korebots.com\/SearchAssist\/how-to\/how-to-apply-semantic-meanings\/","title":{"rendered":"How to Apply Semantic Meanings"},"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.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">SearchAssist\u2019s <\/span><a href=\"https:\/\/docs.google.com\/document\/d\/1A1G6RzvrbxqNQtagGPWiBYSm2sIZaKiB\/edit#bookmark=id.endjhwj5b953\"><span style=\"font-weight: 400;\">Indexing Pipeline<\/span><\/a><span style=\"font-weight: 400;\"> 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 inserts of free text and saves them in a dense vector field. SearchAssist uses these embeddings to rank the documents by semantic relevance. <\/span><span style=\"font-weight: 400;\">The dense vectors are then indexed in the search\u00a0 and similarity is obtained between the user\u2019s query vector and the indexed content vector.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Currently you can apply semantic meanings only only on\u00a0 web content source.\u00a0<\/span><span style=\"font-weight: 400;\">When SearchAssist semantically interprets the source from natural language\u00a0 perspective, the relevant results get priority over others.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">You can:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Add multiple semantics to be analyzed from the source field.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Define a condition for the semantic meaning stage. The semantics from only the documents that satisfy the given condition would be analyzed.\u00a0\u00a0<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Re-order or delete semantic meaning rules.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Simulate the changes before saving them.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Ensure to click <\/span><b>Train your App<\/b><span style=\"font-weight: 400;\"> each time you make changes to any index configuration. This builds the index based on the updated configurations.<a ref=\"magnificPopup\" href=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Train_your_App_icon.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-1605 size-full\" src=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Train_your_App_icon.png\" alt=\"\" width=\"460\" height=\"59\" srcset=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Train_your_App_icon.png 460w, https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Train_your_App_icon-300x38.png 300w\" sizes=\"(max-width: 460px) 100vw, 460px\" \/><\/a><\/span><\/p>\n<p><span style=\"font-weight: 400;\">Configuration<\/span><\/p>\n<p><span style=\"font-weight: 400;\">To configure for applying semantic meaning, take the following 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;\">Select <\/span><b>Semantic Meaning<\/b><span style=\"font-weight: 400;\"> from the <\/span><b>Stage Type<\/b><span style=\"font-weight: 400;\"> dropdown list.<a ref=\"magnificPopup\" href=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-1644 size-medium\" src=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning1-300x274.png\" alt=\"\" width=\"300\" height=\"274\" srcset=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning1-300x274.png 300w, https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning1.png 490w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/a><\/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. SearchAssists considers only the documents that satisfy the conditions as part of the stage. Refer <\/span><a href=\"https:\/\/docs.google.com\/document\/d\/1A1G6RzvrbxqNQtagGPWiBYSm2sIZaKiB\/edit#bookmark=id.vwezm53de2kr\"><span style=\"font-weight: 400;\">Conditions for Applying Semantic Meanings<\/span><\/a><span style=\"font-weight: 400;\">.<\/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><span style=\"font-weight: 400;\">.<\/span><\/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><span style=\"font-weight: 400;\">. This field is created by the application.\u00a0<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Choose a model from the <\/span><b>Choose Model<\/b><span style=\"font-weight: 400;\"> dropdown list.<\/span><a href=\"https:\/\/docs.google.com\/document\/d\/1A1G6RzvrbxqNQtagGPWiBYSm2sIZaKiB\/edit#bookmark=id.fskscspyw9nx\"><span style=\"font-weight: 400;\"> See here<\/span><\/a><span style=\"font-weight: 400;\"> for details. <a ref=\"magnificPopup\" href=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-1645 size-large\" src=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning2-1024x490.png\" alt=\"\" width=\"640\" height=\"306\" srcset=\"https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning2-1024x490.png 1024w, https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning2-300x143.png 300w, https:\/\/multisite.korebots.com\/SearchAssist\/wp-content\/uploads\/sites\/18\/2021\/12\/Manage_indices_wb_semantic-meaning2.png 1660w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/><\/a><\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Click <\/span><b>Simulate<\/b><span style=\"font-weight: 400;\"> 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 there is no mention in the condition and the number of documents.<\/span><\/li>\n<li style=\"font-weight: 400;\"><span style=\"font-weight: 400;\">Once ready, click <\/span><b>Save Configuration<\/b><span style=\"font-weight: 400;\"> on the upper-right.<\/span><\/li>\n<\/ol>\n<p><span style=\"font-weight: 400;\">Supported Models in Semantic Analysis<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The following models are supported:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\"><b>Universal Sentence Encoder<\/b><span style=\"font-weight: 400;\"> \u2013 It encodes text into high-dimensional vectors that are used for semantic similarity.<\/span><\/li>\n<li style=\"font-weight: 400;\"><b>Sentence Transformers<\/b><span style=\"font-weight: 400;\"> \u2013 it&#8217;s a framework for sentence and text embeddings.<\/span><\/li>\n<li style=\"font-weight: 400;\"><b>InferSent<\/b><span style=\"font-weight: 400;\"> \u2013 it&#8217;s a sentence embedding method that provides semantic sentence representations.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Conditions for Semantic Analysis<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Condition is of the following format: <\/span><span style=\"font-weight: 400;\">ctx.fieldtype==value<\/span><span style=\"font-weight: 400;\"> or <\/span><span style=\"font-weight: 400;\">ctx.fieldtype!=value<\/span><span style=\"font-weight: 400;\">. The <\/span><i><span style=\"font-weight: 400;\">field_name<\/span><\/i><span style=\"font-weight: 400;\"> can be obtained from the Fields table under Index Configuration.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">For example, <\/span><span style=\"font-weight: 400;\">ctx.contentType==&#8221;web&#8221;<\/span><span style=\"font-weight: 400;\"> to restrict the extraction to the content from a web source.<\/span><\/p>\n<p>&nbsp;<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/section><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=\"w-post-elm post_navigation layout_simple inv_false\"><a class=\"post_navigation-item order_first to_prev\" href=\"https:\/\/multisite.korebots.com\/SearchAssist\/how-to\/how-to-extract-entities\/\" title=\"How to Extract Entities\"><div class=\"post_navigation-item-arrow\"><\/div><div class=\"post_navigation-item-meta\">Previous Post<\/div><div class=\"post_navigation-item-title\"><span>How to Extract Entities<\/span><\/div><\/a><a class=\"post_navigation-item order_second to_next\" href=\"https:\/\/multisite.korebots.com\/SearchAssist\/how-to\/how-to-run-custom-scripts\/\" title=\"How to Run Custom Scripts\"><div class=\"post_navigation-item-arrow\"><\/div><div class=\"post_navigation-item-meta\">Next Post<\/div><div class=\"post_navigation-item-title\"><span>How to Run Custom Scripts<\/span><\/div><\/a><\/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.\u00a0 SearchAssist\u2019s Indexing Pipeline supports a Semantic Meaning stage. This stage uses Deep Neural Network algorithms to create inserts of free text and saves them in a dense vector field. SearchAssist uses these embeddings to rank the documents by...","protected":false},"author":18,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[59,58],"tags":[],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/1642"}],"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\/18"}],"replies":[{"embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/comments?post=1642"}],"version-history":[{"count":7,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/1642\/revisions"}],"predecessor-version":[{"id":2711,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/posts\/1642\/revisions\/2711"}],"wp:attachment":[{"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/media?parent=1642"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/categories?post=1642"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/multisite.korebots.com\/SearchAssist\/wp-json\/wp\/v2\/tags?post=1642"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}