{"id":1490,"date":"2019-03-03T11:02:21","date_gmt":"2019-03-03T05:32:21","guid":{"rendered":"https:\/\/www.rangakrish.com\/?p=1490"},"modified":"2019-03-03T15:03:14","modified_gmt":"2019-03-03T09:33:14","slug":"text-summarization-apis","status":"publish","type":"post","link":"https:\/\/www.rangakrish.com\/index.php\/2019\/03\/03\/text-summarization-apis\/","title":{"rendered":"Text Summarization APIs"},"content":{"rendered":"<p>I talked about detecting\u00a0<em><strong>E<\/strong><strong>motion<\/strong><\/em>\u00a0from text in the last two <a href=\"https:\/\/www.rangakrish.com\/index.php\/2019\/02\/17\/identifying-emotions-from-text\/\" target=\"_blank\" rel=\"noopener\"><em><strong>articles<\/strong><\/em><\/a>. Another popular text analysis service is <em><strong>Text Summarization<\/strong><\/em>.<span class=\"Apple-converted-space\">\u00a0<\/span><\/p>\n<p>There are two approaches for summarization:<\/p>\n<ul>\n<li><span style=\"color: #0000ff;\">Extractive summarization<\/span><\/li>\n<li><span style=\"color: #0000ff;\">Abstractive summarization<\/span><\/li>\n<\/ul>\n<p>In the first approach, <em><strong>&#8220;Extractive Summarization&#8221;<\/strong><\/em>, the system extracts key sentences from the given text and puts them together to form a summary. There are no new words or phrases in the summary. This is the widely used approach today. An algorithm called <em><strong>&#8220;TextRank&#8221;<\/strong><\/em> is the inspiration for many such implementations. You can read more about this approach <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2018\/11\/introduction-text-summarization-textrank-python\/\" target=\"_blank\" rel=\"noopener\"><em><strong>here<\/strong><\/em><\/a>.<\/p>\n<p>The second approach, <em><strong>&#8220;Abstractive Summarization&#8221;<\/strong><\/em> attempts to <em><strong>&#8220;understand&#8221;<\/strong><\/em> what is being discussed in the given text, in order to generate a summary that usually includes new words and phrases. Remember, we humans are good at summarizing given text\u00a0<em><strong>&#8220;in our own words&#8221;<\/strong><\/em>. This is a challenging research problem, and a lot of focus is currently on this topic.<\/p>\n<p>Today, I am going to take a sample text and run it through three different <em><strong>Summarization APIs<\/strong><\/em> and look at the output generated by them. The three <em><strong>API<\/strong><\/em> services I am going to use are:<\/p>\n<ul>\n<li><span style=\"color: #0000ff;\"><a href=\"https:\/\/www.meaningcloud.com\" target=\"_blank\" rel=\"noopener\">MeaningCloud.com<\/a>\u00a0<\/span><\/li>\n<li><span style=\"color: #0000ff;\"><a href=\"https:\/\/aylien.com\" target=\"_blank\" rel=\"noopener\">Aylien.com<\/a>\u00a0<\/span><\/li>\n<li><span style=\"color: #0000ff;\"><a href=\"https:\/\/deepai.org\" target=\"_blank\" rel=\"noopener\">Deepai.org<\/a>\u00a0<\/span><\/li>\n<\/ul>\n<p>I have written an <a href=\"https:\/\/www.rangakrish.com\/index.php\/2018\/12\/09\/parsing-text-with-meaningclouds-text-analytics-api\/\" target=\"_blank\" rel=\"noopener\"><em><strong>article<\/strong><\/em><\/a>\u00a0earlier describing <em><strong>MeaningCloud&#8217;s Parsing API<\/strong><\/em>. This Madrid-based company offers a variety of text analysis APIs.<\/p>\n<p>The input for summarization is an article based on <em><strong>Florence Nightingale<\/strong><\/em> and is taken from this <a href=\"https:\/\/simple.wikipedia.org\/wiki\/Florence_Nightingale\" target=\"_blank\" rel=\"noopener\"><em><strong>page<\/strong><\/em><\/a>.<span class=\"Apple-converted-space\">\u00a0 <\/span>I copy-pasted the text onto <em><strong>NotePad<\/strong><\/em> (Windows app) and removed a couple of non-ascii characters so that the final text has only ascii characters (this is not a requirement for generating summary, though).<\/p>\n<h2><b>MeaningCloud.com<\/b><\/h2>\n<p>Working with <em><strong>MeaningCloud<\/strong><\/em> was easy. I logged into my account and pasted the input text in the <em><strong>&#8220;Test Console&#8221;<\/strong><\/em> corresponding to <em><strong>Text Summarization API<\/strong><\/em>. The nice thing is that there is an option to specify the number of sentences in the generated summary, and I chose the default (5 sentences). Here is the generated summary:<\/p>\n<blockquote><p><span lang=\"EN-IN\" style=\"color: #0000ff;\">Nightingale was helped to understand statistics by her country&#8217;s leading expert on public statistics,. Cholera is caused by a bacterium spread by people drinking water contaminated by sewage. Florence Nightingale was born into an upper class British family in 1820 in Florence, Tuscany, Italy. In 1907, Florence Nightingale became the first woman to be awarded the Order of Merit by King Edward VII. In London and a Florence Nightingale museum, also in London.<\/span><\/p><\/blockquote>\n<p>Just to make it interesting, I ran the summarizer again, with the option to emit 10 sentences this time. Here is the result:<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">Florence Nightingale, OM (12 May 1820 &#8211; 13 August 1910), was an English nurse. Florence Nightingale was a wonderful woman. Nightingale was helped to understand statistics by her country&#8217;s leading expert on public statistics,. Cholera is caused by a bacterium spread by people drinking water contaminated by sewage. Florence Nightingale was born into an upper class British family in 1820 in Florence, Tuscany, Italy. In 1854 when the Crimean War began, Florence was working in Harley Street in London. Hospital in Istanbul where the injured soldiers were sent, Florence realized that soldiers died more often. In 1907, Florence Nightingale became the first woman to be awarded the Order of Merit by King Edward VII. Nightingale died in 1910 in London. In London and a Florence Nightingale museum, also in London.<\/span><\/p><\/blockquote>\n<h2><b>Aylien.com<\/b><\/h2>\n<p>Just as I did with <em><strong>MeaningCloud<\/strong><\/em>, I logged into <em><strong>Aylien&#8217;s<\/strong><\/em> account and submitted the article. In this case, I had to submit the <em><strong>URL<\/strong><\/em> of the article. I chose the default summary size of 5 sentences and here is the output :<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">Florence Nightingale, OM (12 May 1820 \u2013 13 August 1910), was an English nurse.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">In 1854 when the Crimean War began, Florence was working in Harley Street in London.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">At the hospital in Istanbul where the injured soldiers were sent, Florence realized that soldiers died more often from diseases like cholera than from their injuries in war.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">She used her knowledge of maths and statistics to show the British government that providing better conditions for sick and injured soldiers would help them win the war.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">There are many statues of her in Britain, including one in Waterloo Place in London and a Florence Nightingale museum, also in London.<\/span><\/p><\/blockquote>\n<p>When I chose 10 sentences as the summary size, this is what I got:<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">Florence Nightingale, OM (12 May 1820 \u2013 13 August 1910), was an English nurse.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">She became a leader of the team of nurses who helped wounded soldiers during the Crimean War.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Florence Nightingale was a wonderful woman who fought the odds of not living a life expected by her family.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Florence Nightingale was born into an upper class British family in 1820 in Florence, Tuscany, Italy.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">In 1854 when the Crimean War began, Florence was working in Harley Street in London.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">At the hospital in Istanbul where the injured soldiers were sent, Florence realized that soldiers died more often from diseases like cholera than from their injuries in war.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">She used her knowledge of maths and statistics to show the British government that providing better conditions for sick and injured soldiers would help them win the war.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Nightingale believed religion helped provide people with the fortitude for arduous good work.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">In 1907, Florence Nightingale became the first woman to be awarded the Order of Merit by King Edward VII.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">There are many statues of her in Britain, including one in Waterloo Place in London and a Florence Nightingale museum, also in London.<\/span><\/p><\/blockquote>\n<h2><b>Deepai.org<\/b><\/h2>\n<p>In the case of <em><strong>Deep AI<\/strong><\/em>, there is no option to control the number of sentences in the generated summary. The documentation says that the summary is about <em><strong>20 percent<\/strong><\/em> of the original text. I logged into my account and pasted the input text in the test console. Here is the generated summary:<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">Florence Nightingale, OM (12 May 1820\u00a0 &#8211; 13 August 1910), was an English nurse.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">helped wounded soldiers during the Crimean War.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Florence Nightingale was a wonderful woman<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Nightingale was helped to understand statistics by her country&#8217;s leading expert on public statistics,\u00a0<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Unfortunately, both she and Farr believed the disease was caused by foul air: this was called the miasma theory.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Florence Nightingale was born into an upper class British family in 1820 in Florence, Tuscany, Italy.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">In 1854 when the Crimean War began, Florence was working in Harley Street in London.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">hospital in Istanbul where the injured soldiers were sent, Florence realized that soldiers died more often<\/span><\/p>\n<p><span style=\"color: #0000ff;\">show the British government that providing better conditions for sick and injured soldiers would help them<\/span><\/p>\n<p><span style=\"color: #0000ff;\">There is a syndrome named after her called &#8220;Florence Nightingale Syndrome&#8221;.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Nightingale believed religion helped provide people with<\/span><\/p>\n<p><span style=\"color: #0000ff;\">In 1907, Florence Nightingale became the first woman to be awarded the Order of Merit by King Edward VII.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">Nightingale died in 1910 in London.<\/span><\/p>\n<p><span style=\"color: #0000ff;\">in London and a Florence Nightingale museum, also in London.<\/span><\/p><\/blockquote>\n<p>The summary has 14 sentences.<\/p>\n<h2><b>Observations<\/b><\/h2>\n<p>Let us discard the 5-sentence summaries from <em><strong>MeaningCloud<\/strong><\/em> and <em><strong>Aylien<\/strong><\/em> and consider only the 10-sentence versions. That way, the output from all three API services are of <em><strong>&#8220;similar&#8221;<\/strong><\/em> size.<\/p>\n<p>You can detect substantial similarity in the summaries generated by <em><strong>MeaningCloud<\/strong><\/em> and <em><strong>Deep AI<\/strong><\/em>. In fact, except for the sentence <span style=\"color: #0000ff;\"><em><strong>&#8220;Cholera is caused by a bacterium spread by people drinking water contaminated by sewage.&#8221;<\/strong><\/em><\/span>, every sentence in the summary of <em><strong>MeaningCloud<\/strong><\/em> is also in the summary of <em><strong>Deep AI<\/strong><\/em>. Of course, <em><strong>Deep AI<\/strong><\/em> has a few extra sentences (total size is 14) as I pointed out earlier.<\/p>\n<p>What is interesting is that some of the sentences in both the summaries are <em><strong>truncated<\/strong><\/em> versions of the original sentences. For example, the actual sentence<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">&#8220;Nightingale was helped to understand statistics by her country&#8217;s leading expert on public statistics,<span class=\"Apple-converted-space\">\u00a0 <\/span>William Farr.&#8221;<\/span><span class=\"Apple-converted-space\">\u00a0<\/span><\/p><\/blockquote>\n<p>has been trucated to:<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">&#8220;Nightingale was helped to understand statistics by her country&#8217;s leading expert on public statistics,.&#8221;<\/span><span class=\"Apple-converted-space\">\u00a0<\/span><\/p><\/blockquote>\n<p>As another example, the original sentence<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">&#8220;She became a leader of the team of nurses who helped wounded soldiers during the Crimean War.&#8221;<\/span><\/p><\/blockquote>\n<p>has become:<\/p>\n<blockquote><p><span style=\"color: #0000ff;\">&#8220;helped wounded soldiers during the Crimean War.&#8221;<\/span><\/p><\/blockquote>\n<p>It is not clear why this happens.<\/p>\n<p>In terms of the overall output, I prefer the summary produced by <em><strong>Aylien<\/strong><\/em>. It appears a bit more <em>coherent<\/em> than the other two.<\/p>\n<p>What if we asked two people to generate <em><strong>&#8220;extractive summarization&#8221;<\/strong><\/em> manually? Will their output match that of <em><strong>Aylien<\/strong><\/em>? My guess is that there is likely to be variation even among human generated summaries, because identifying <em><strong>&#8220;important&#8221;<\/strong><\/em> sentences in a given piece of text is somewhat subjective. Secondly, even if two people choose the same set of sentences, they might <em><strong>rearrange<\/strong><\/em> them in slightly different order.<span class=\"Apple-converted-space\">\u00a0<\/span><\/p>\n<p>In the meantime, while we are eagerly waiting for good quality <em><strong>&#8220;abstractive summarization&#8221;<\/strong><\/em> implementations, we have to make do with <em><strong>&#8220;extractive summarization&#8221;<\/strong><\/em>.<\/p>\n<p>Have a nice weekend!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I talked about detecting\u00a0Emotion\u00a0from text in the last two articles. Another popular text analysis service is Text Summarization.\u00a0 There are two approaches for summarization: Extractive summarization Abstractive summarization In the first approach, &#8220;Extractive Summarization&#8221;, the system extracts key sentences from the given text and puts them together to form a summary. There are no new [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"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":[107],"tags":[174,194,193],"class_list":["post-1490","post","type-post","status-publish","format-standard","hentry","category-natural-language-processing","tag-natural-language-processing","tag-text-analysis","tag-text-summarization"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p9OLnF-o2","jetpack-related-posts":[{"id":1541,"url":"https:\/\/www.rangakrish.com\/index.php\/2019\/04\/21\/textcontents-function-in-mathematica-12\/","url_meta":{"origin":1490,"position":0},"title":"TextContents[ ] Function in Mathematica 12","author":"admin","date":"April 21, 2019","format":false,"excerpt":"Mathematica 12 was released a few days ago.\u00a0 It has been over a year since version 11.3 came out in March 2018. The long wait appears justified since the new release boasts of numerous improvements and new features across several areas. You may want to read this blog post\u00a0by Stephen\u2026","rel":"","context":"In &quot;Mathematica&quot;","block_context":{"text":"Mathematica","link":"https:\/\/www.rangakrish.com\/index.php\/category\/mathematica\/"},"img":{"alt_text":"Importing Text File","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2019\/04\/FileImport.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2019\/04\/FileImport.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2019\/04\/FileImport.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":1863,"url":"https:\/\/www.rangakrish.com\/index.php\/2020\/01\/02\/book-review-automatic-text-simplification\/","url_meta":{"origin":1490,"position":1},"title":"Book Review &#8211; Automatic Text Simplification","author":"admin","date":"January 2, 2020","format":false,"excerpt":"Title: Automatic Text Simplification Author: Horacio Saggino Publisher: Morgan & Claypool Publishers Year: 2017 Automatic Text Simplification is an active area of research in NLP and has been going on for over 20 years. The idea is to transform a given text T1 into text T2 such that T2 is\u2026","rel":"","context":"In &quot;Book Review&quot;","block_context":{"text":"Book Review","link":"https:\/\/www.rangakrish.com\/index.php\/category\/book-review\/"},"img":{"alt_text":"Automatic Text Simplification","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2020\/01\/IMG_1496-edited-225x300.jpeg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":1285,"url":"https:\/\/www.rangakrish.com\/index.php\/2018\/12\/09\/parsing-text-with-meaningclouds-text-analytics-api\/","url_meta":{"origin":1490,"position":2},"title":"Parsing Text with MeaningCloud&#8217;s Text Analytics API","author":"admin","date":"December 9, 2018","format":false,"excerpt":"There is wide-spread interest in Natural Language Processing (NLP) today, and there are several API services available to cater to this demand. See this article for a fairly detailed list of services. All of them support multiple languages, including English. Today, I am going to share my experience in working\u2026","rel":"","context":"In &quot;LISP&quot;","block_context":{"text":"LISP","link":"https:\/\/www.rangakrish.com\/index.php\/category\/lisp\/"},"img":{"alt_text":"Get Words Function","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2018\/12\/Get-words.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2018\/12\/Get-words.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2018\/12\/Get-words.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":884,"url":"https:\/\/www.rangakrish.com\/index.php\/2018\/04\/08\/natural-language-generation\/","url_meta":{"origin":1490,"position":3},"title":"Natural Language Generation","author":"admin","date":"April 8, 2018","format":false,"excerpt":"I had written a series of posts on my iLangGen framework last year. It aims to provide a flexible and expressive approach for building natural language generation systems. In today's post, I would like to describe a concrete example of how iLangGen can be used for generating natural language text\u2026","rel":"","context":"In &quot;LISP&quot;","block_context":{"text":"LISP","link":"https:\/\/www.rangakrish.com\/index.php\/category\/lisp\/"},"img":{"alt_text":"Overall Approach","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2018\/04\/overall-1.png?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":1309,"url":"https:\/\/www.rangakrish.com\/index.php\/2018\/12\/16\/generating-poetry-using-rita\/","url_meta":{"origin":1490,"position":4},"title":"Generating Poetry Using RiTa","author":"admin","date":"December 16, 2018","format":false,"excerpt":"A few days ago, I came across a nice library called RiTa, which is described as a software toolkit for computational literature. Its two major features are text analysis and text generation.\u00a0 The text analysis module parses given text to extract sentences, tokens, POS, stresses, and phonemes. There is also\u2026","rel":"","context":"In &quot;Natural Language Processing&quot;","block_context":{"text":"Natural Language Processing","link":"https:\/\/www.rangakrish.com\/index.php\/category\/natural-language-processing\/"},"img":{"alt_text":"Terminal Session","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2018\/12\/Terminal.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":328,"url":"https:\/\/www.rangakrish.com\/index.php\/2016\/09\/11\/natural-language-processing-in-mathematica\/","url_meta":{"origin":1490,"position":5},"title":"Natural Language Processing in Mathematica","author":"admin","date":"September 11, 2016","format":false,"excerpt":"Welcome back. Today I am going to share with you some of the nice capabilities of Mathematica in the area of Natural Language Processing (NLP). Let us start with words. What if we wish to know\u00a0the various definitions of the word image?\u00a0Here is the answer. Mathematica gives the various senses\u2026","rel":"","context":"In &quot;Mathematica&quot;","block_context":{"text":"Mathematica","link":"https:\/\/www.rangakrish.com\/index.php\/category\/mathematica\/"},"img":{"alt_text":"Word Definition","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2016\/09\/word-data1-1024x238.png?resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2016\/09\/word-data1-1024x238.png?resize=350%2C200 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2016\/09\/word-data1-1024x238.png?resize=525%2C300 1.5x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2016\/09\/word-data1-1024x238.png?resize=700%2C400 2x"},"classes":[]}],"_links":{"self":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts\/1490","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/comments?post=1490"}],"version-history":[{"count":0,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts\/1490\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/media?parent=1490"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/categories?post=1490"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/tags?post=1490"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}