{"id":23817,"date":"2015-04-24T17:23:23","date_gmt":"2015-04-24T22:23:23","guid":{"rendered":"http:\/\/www.dannyadam.com\/blog\/?p=23817"},"modified":"2019-11-06T18:04:32","modified_gmt":"2019-11-06T23:04:32","slug":"article-highlighter","status":"publish","type":"post","link":"https:\/\/www.dannyadam.com\/blog\/2015\/04\/article-highlighter\/","title":{"rendered":"Article Highlighter"},"content":{"rendered":"<p><em>Auto Highlight<\/em> is a Chrome extension that automatically highlights the important content on article pages.<\/p>\n<p>Here&#8217;s a link to the extension:<br \/>\n<a href=\"https:\/\/chrome.google.com\/webstore\/detail\/highlight\/dnkdpcbijfnmekbkchfjapfneigjomhh\">https:\/\/<wbr \/>chrome.google.com\/<wbr \/>webstore\/<wbr \/>detail\/<wbr \/>highlight\/<wbr \/>dnkdpcbijfnmekbkchfjapfneigjomhh<\/a><\/p>\n<p>The source code is on GitHub:<br \/>\n<a href=\"https:\/\/github.com\/dstein64\/highlight\">https:\/\/<wbr \/>github.com\/<wbr \/>dstein64\/<wbr \/>highlight<\/a><\/p>\n<p>After installing the extension, a highlighter icon appears in the location bar. Clicking that icon highlights important content on the page.<\/p>\n<p><a href=\"https:\/\/www.dannyadam.com\/blog\/wp-content\/uploads\/2015\/04\/1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-23821\" src=\"https:\/\/www.dannyadam.com\/blog\/wp-content\/uploads\/2015\/04\/1.png\" alt=\"1\" width=\"1280\" height=\"800\" \/><\/a><\/p>\n<p><!--more--><\/p>\n<p>The extension is based on a separate project that I was recently working on\u00a0for\u00a0an\u00a0<em>adaptive information systems<\/em> course. For my project, I implemented a Chrome extension that learns a user model based on the web pages a user visits. Then on new pages, content was highlighted based on the similarity to the user model. I called the project extension <em>Persightlight<\/em>, for &#8220;personalized highlighting&#8221;.<\/p>\n<p>The personalization component still needs more work, and it added complexity to the code. <em>Auto Highlight<\/em> is based on <em>Persighlight<\/em>, but all the user modeling and personalization code has been removed.\u00a0<em>Auto Highlight<\/em>\u00a0uses a heuristic that gives higher weight to words that appear often, rather than depending on a user model.\u00a0I&#8217;d like to improve <em>Auto Highlight<\/em>, adding ideas from recent NLP research.<\/p>\n<p><em>Persighlight<\/em>\u00a0essentially\u00a0did\u00a0<a href=\"http:\/\/en.wikipedia.org\/wiki\/Automatic_summarization#Extraction-based_summarization\">extraction-based automatic summarization<\/a>, scoring sentences relative to a user model. The model was represented by a term frequency vector, as were sentence candidates. Candidates were scored based on their cosine similarity with the user model.\u00a0I&#8217;d like to also continue work on <em>Persighlight<\/em>. It would be interesting to see how personalization with a user model can contribute to highlighting, and summarization more broadly.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Auto Highlight is a Chrome extension that automatically highlights the important content on article pages. Here&#8217;s a link to the extension: https:\/\/chrome.google.com\/webstore\/detail\/highlight\/dnkdpcbijfnmekbkchfjapfneigjomhh The source code is on GitHub: https:\/\/github.com\/dstein64\/highlight After installing the extension, a highlighter icon appears in the location bar. Clicking that icon highlights important content on the page.<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[1],"tags":[41,40,39],"class_list":["post-23817","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-javascript","tag-nlp","tag-summarization"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_shortlink":"https:\/\/wp.me\/p1sCC6-6c9","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/posts\/23817","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/comments?post=23817"}],"version-history":[{"count":10,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/posts\/23817\/revisions"}],"predecessor-version":[{"id":26142,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/posts\/23817\/revisions\/26142"}],"wp:attachment":[{"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/media?parent=23817"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/categories?post=23817"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dannyadam.com\/blog\/wp-json\/wp\/v2\/tags?post=23817"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}