{"id":203,"date":"2023-10-24T23:32:54","date_gmt":"2023-10-24T18:02:54","guid":{"rendered":"https:\/\/farrukhnaveed.co\/blogs\/?p=203"},"modified":"2023-10-24T23:32:56","modified_gmt":"2023-10-24T18:02:56","slug":"understanding-the-bert-model","status":"publish","type":"post","link":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/","title":{"rendered":"Understanding the BERT Model"},"content":{"rendered":"\n

BERT, which stands for Bidirectional Encoder Representations from Transformers<\/strong>, has revolutionized the world of natural language processing (NLP). Developed by researchers at Google in 2018, BERT provides a deep bidirectional representation of text, allowing it to achieve state-of-the-art results on a multitude of NLP tasks.<\/p>\n\n\n\n

In this article, we’ll dive deep into the BERT model, understand its architecture and functioning, and explore some Python coding examples to implement and utilize BERT.<\/p>\n\n\n\n

1. BERT’s Underlying Architecture: Transformers<\/h2>\n\n\n\n

The foundation of BERT is the Transformer architecture. A transformer uses attention mechanisms to capture contextual information from the entire input sequence in its representation, unlike models such as LSTM or GRU, which read sequentially.<\/p>\n\n\n\n

Attention Mechanism<\/h3>\n\n\n\n

The attention mechanism allows the model to focus on different parts of the input text when producing an output. In essence, it calculates a weight for each input word for a given output word.<\/p>\n\n\n\n

2. What Makes BERT Special: Bidirectionality<\/h2>\n\n\n\n

Traditional language models, like LSTM and GRU, are either unidirectional or combine two unidirectional representations. BERT, on the other hand, is inherently bidirectional. This bidirectionality allows BERT to understand the context of each word in a sentence more holistically.<\/p>\n\n\n\n

For instance, in the sentence “He went to the bank to withdraw money,” the word “bank” can mean a financial institution. But in “He sat by the bank of the river,” “bank” refers to the side of a river. BERT can differentiate between these meanings based on context.<\/p>\n\n\n\n

3. Pre-training and Fine-tuning<\/h2>\n\n\n\n

BERT’s success largely stems from its two-step process:<\/p>\n\n\n\n

    \n
  1. Pre-training:<\/strong> BERT is first trained on a large corpus (like the entire Wikipedia) using masked language modeling. Some words in a sentence are masked, and the model tries to predict them based on surrounding words.<\/li>\n\n\n\n
  2. Fine-tuning:<\/strong> For specific tasks, BERT is then fine-tuned on task-specific data. This process allows BERT to be adapted to a wide variety of tasks with relatively small datasets.<\/li>\n<\/ol>\n\n\n\n

    4. BERT Variants<\/h2>\n\n\n\n

    BERT comes in various sizes:<\/p>\n\n\n\n

      \n
    • BERT-Base<\/li>\n\n\n\n
    • BERT-Large<\/li>\n\n\n\n
    • And others, like DistilBERT (a distilled, smaller version of BERT)<\/li>\n<\/ul>\n\n\n\n

      Each variant has a trade-off between computational intensity and accuracy.<\/p>\n\n\n\n

      Python Coding Examples with BERT<\/h2>\n\n\n\n

      Now, let’s see BERT in action with some Python coding examples. For this, we’ll use the transformers<\/code> library, which provides easy-to-use implementations of BERT and other transformer models.<\/p>\n\n\n\n

      Installing the library:<\/h3>\n\n\n\n
      <\/circle><\/circle><\/circle><\/g><\/svg><\/span><\/path><\/path><\/svg><\/span>
      !<\/span>pip install transformers<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n
      Tokenizing Input:<\/h3>\n\n\n\n
      Before feeding text to BERT, it needs to be tokenized:<\/p>\n\n\n\n
      <\/circle><\/circle><\/circle><\/g><\/svg><\/span><\/path><\/path><\/svg><\/span>
      from<\/span> transformers <\/span>import<\/span> BertTokenizer<\/span><\/span>\n<\/span>\ntokenizer <\/span>=<\/span> BertTokenizer<\/span>.<\/span>from_pretrained<\/span>(<\/span>'<\/span>bert-base-uncased<\/span>'<\/span>)<\/span><\/span>\ntokens <\/span>=<\/span> tokenizer<\/span>.<\/span>tokenize<\/span>(<\/span>"<\/span>Hello, BERT!<\/span>"<\/span>)<\/span><\/span>\nprint<\/span>(<\/span>tokens<\/span>)<\/span><\/span>\n<\/span><\/code><\/pre><\/div>\n\n\n\n
      Output:<\/p>\n\n\n\n
      <\/circle><\/circle><\/circle><\/g><\/svg><\/span><\/path><\/path><\/svg><\/span>
      [<\/span>'<\/span>hello<\/span>'<\/span>,<\/span> <\/span>'<\/span>,<\/span>'<\/span>,<\/span> <\/span>'<\/span>bert<\/span>'<\/span>,<\/span> <\/span>'<\/span>!<\/span>'<\/span>]<\/span><\/span><\/code><\/pre><\/div>\n\n\n\n
      Extracting Embeddings:<\/h3>\n\n\n\n
      Here’s how you can get BERT embeddings for a piece of text:<\/p>\n\n\n\n
      <\/circle><\/circle><\/circle><\/g><\/svg><\/span><\/path><\/path><\/svg><\/span>
      from<\/span> transformers <\/span>import<\/span> BertModel<\/span><\/span>\n<\/span>\n# Tokenizing input<\/span><\/span>\ntext <\/span>=<\/span> <\/span>"<\/span>Hello, BERT!<\/span>"<\/span><\/span>\ntokens <\/span>=<\/span> tokenizer<\/span>.<\/span>tokenize<\/span>(<\/span>text<\/span>)<\/span><\/span>\ntoken_ids <\/span>=<\/span> tokenizer<\/span>.<\/span>convert_tokens_to_ids<\/span>(<\/span>tokens<\/span>)<\/span><\/span>\ntoken_ids <\/span>=<\/span> tokenizer<\/span>.<\/span>encode<\/span>(<\/span>text<\/span>,<\/span> <\/span>add_special_tokens<\/span>=True<\/span>)<\/span>  <\/span># Adds [CLS] and [SEP] tokens<\/span><\/span>\n<\/span>\nmodel <\/span>=<\/span> BertModel<\/span>.<\/span>from_pretrained<\/span>(<\/span>'<\/span>bert-base-uncased<\/span>'<\/span>)<\/span><\/span>\nwith<\/span> torch<\/span>.<\/span>no_grad<\/span>():<\/span><\/span>\n    outputs <\/span>=<\/span> <\/span>model<\/span>(<\/span>torch<\/span>.<\/span>tensor<\/span>([<\/span>token_ids<\/span>]))<\/span><\/span>\n    embeddings <\/span>=<\/span> outputs<\/span>.<\/span>last_hidden_state<\/span><\/span>\n<\/span>\nprint<\/span>(<\/span>embeddings<\/span>[<\/span>0<\/span>])<\/span><\/span>\n<\/span><\/code><\/pre><\/div>\n\n\n\n
      Fine-tuning for Classification:<\/h3>\n\n\n\n
      For tasks like sentiment analysis, you can fine-tune BERT:<\/p>\n\n\n\n
      <\/circle><\/circle><\/circle><\/g><\/svg><\/span><\/path><\/path><\/svg><\/span>
      from<\/span> transformers <\/span>import<\/span> BertForSequenceClassification<\/span><\/span>\n<\/span>\n# Assume train_data is a list of tuples with (text, label)<\/span><\/span>\ntrain_data <\/span>=<\/span> <\/span>[(<\/span>"<\/span>This is great!<\/span>"<\/span>,<\/span> <\/span>1<\/span>),<\/span> <\/span>(<\/span>"<\/span>I didn't like it.<\/span>"<\/span>,<\/span> <\/span>0<\/span>)]<\/span><\/span>\n<\/span>\ntokenizer <\/span>=<\/span> BertTokenizer<\/span>.<\/span>from_pretrained<\/span>(<\/span>'<\/span>bert-base-uncased<\/span>'<\/span>)<\/span><\/span>\nmodel <\/span>=<\/span> BertForSequenceClassification<\/span>.<\/span>from_pretrained<\/span>(<\/span>'<\/span>bert-base-uncased<\/span>'<\/span>,<\/span> <\/span>num_labels<\/span>=<\/span>2<\/span>)<\/span><\/span>\n<\/span>\n# Convert data to appropriate format<\/span><\/span>\ninput_ids <\/span>=<\/span> <\/span>[<\/span>tokenizer<\/span>.<\/span>encode<\/span>(<\/span>text<\/span>,<\/span> <\/span>add_special_tokens<\/span>=True<\/span>)<\/span> <\/span>for<\/span> text<\/span>,<\/span> label <\/span>in<\/span> train_data<\/span>]<\/span><\/span>\nlabels <\/span>=<\/span> torch<\/span>.<\/span>tensor<\/span>([<\/span>label <\/span>for<\/span> text<\/span>,<\/span> label <\/span>in<\/span> train_data<\/span>])<\/span><\/span>\n<\/span>\n# Train model (a simple example, in reality, you'd use a DataLoader and optimize over batches)<\/span><\/span>\noptimizer <\/span>=<\/span> torch<\/span>.<\/span>optim<\/span>.<\/span>AdamW<\/span>(<\/span>model<\/span>.<\/span>parameters<\/span>(),<\/span> <\/span>lr<\/span>=<\/span>1e-5<\/span>)<\/span><\/span>\n<\/span>\nfor<\/span> epoch <\/span>in<\/span> <\/span>range<\/span>(<\/span>3<\/span>):<\/span><\/span>\n    model<\/span>.<\/span>train<\/span>()<\/span><\/span>\n    <\/span>for<\/span> i<\/span>,<\/span> <\/span>(<\/span>input_id<\/span>,<\/span> label<\/span>)<\/span> <\/span>in<\/span> <\/span>enumerate<\/span>(<\/span>zip<\/span>(<\/span>input_ids<\/span>,<\/span> labels<\/span>)):<\/span><\/span>\n        outputs <\/span>=<\/span> <\/span>model<\/span>(<\/span>torch<\/span>.<\/span>tensor<\/span>([<\/span>input_id<\/span>]),<\/span> <\/span>labels<\/span>=<\/span>torch<\/span>.<\/span>tensor<\/span>([<\/span>label<\/span>]))<\/span><\/span>\n        loss <\/span>=<\/span> outputs<\/span>.<\/span>loss<\/span><\/span>\n        loss<\/span>.<\/span>backward<\/span>()<\/span><\/span>\n        optimizer<\/span>.<\/span>step<\/span>()<\/span><\/span>\n        optimizer<\/span>.<\/span>zero_grad<\/span>()<\/span><\/span>\n<\/span>\n# Save the model<\/span><\/span>\nmodel<\/span>.<\/span>save_pretrained<\/span>(<\/span>'<\/span>.\/sentiment_model<\/span>'<\/span>)<\/span><\/span>\n<\/span><\/code><\/pre><\/div>\n\n\n\n
      Conclusion:<\/h2>\n\n\n\n
      BERT has undoubtedly become one of the cornerstones of modern NLP, providing a versatile approach to understanding the intricacies of human language. Whether you’re just starting or are a seasoned practitioner, the power and adaptability of BERT, combined with libraries like transformers<\/code>, enable a wide range of NLP applications.<\/p>\n","protected":false},"excerpt":{"rendered":"
      BERT, which stands for Bidirectional Encoder Representations from Transformers, has revolutionized the world of natural language processing (NLP). Developed by researchers at Google in 2018, […]<\/p>\n","protected":false},"author":1,"featured_media":204,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[24,38,5],"class_list":["post-203","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","tag-ai","tag-bert","tag-python"],"yoast_head":"\nUnderstanding the BERT Model - Farrukh's Tech Space<\/title>\n<meta name=\"description\" content=\"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Understanding the BERT Model - Farrukh's Tech Space\" \/>\n<meta property=\"og:description\" content=\"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\" \/>\n<meta property=\"og:site_name\" content=\"Farrukh's Tech Space\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-24T18:02:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-24T18:02:56+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/10\/Bert-Model.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"627\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Farrukh Naveed Anjum\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:description\" content=\"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/10\/Bert-Model.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Farrukh Naveed Anjum\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\"},\"author\":{\"name\":\"Farrukh Naveed Anjum\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29\"},\"headline\":\"Understanding the BERT Model\",\"datePublished\":\"2023-10-24T18:02:54+00:00\",\"dateModified\":\"2023-10-24T18:02:56+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\"},\"wordCount\":474,\"publisher\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\"},\"keywords\":[\"AI\",\"BERT\",\"Python\"],\"articleSection\":[\"AI\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\",\"name\":\"Understanding the BERT Model - Farrukh's Tech Space\",\"isPartOf\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#website\"},\"datePublished\":\"2023-10-24T18:02:54+00:00\",\"dateModified\":\"2023-10-24T18:02:56+00:00\",\"description\":\"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.\",\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/\"]}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#website\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/\",\"name\":\"Farrukh Naveed Anjum Blogs\",\"description\":\"Empowering Software Architects with Knowledge on Big Data and AI\",\"publisher\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/farrukhnaveed.co\/blogs\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#organization\",\"name\":\"Farrukh Naveed Anjum Blogs\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg\",\"contentUrl\":\"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg\",\"width\":1707,\"height\":2560,\"caption\":\"Farrukh Naveed Anjum Blogs\"},\"image\":{\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29\",\"name\":\"Farrukh Naveed Anjum\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g\",\"caption\":\"Farrukh Naveed Anjum\"},\"description\":\"Full Stack Developer and Software Architect with 14 years of experience in various domains, including Enterprise Resource Planning, Data Retrieval, Web Scraping, Real-Time Analytics, Cybersecurity, NLP, ED-Tech, and B2B Price Comparison\",\"sameAs\":[\"https:\/\/farrukhnaveed.co\/blog\"],\"url\":\"https:\/\/farrukhnaveed.co\/blogs\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Understanding the BERT Model - Farrukh's Tech Space","description":"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/","og_locale":"en_US","og_type":"article","og_title":"Understanding the BERT Model - Farrukh's Tech Space","og_description":"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.","og_url":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/","og_site_name":"Farrukh's Tech Space","article_published_time":"2023-10-24T18:02:54+00:00","article_modified_time":"2023-10-24T18:02:56+00:00","og_image":[{"width":1200,"height":627,"url":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/10\/Bert-Model.jpg","type":"image\/jpeg"}],"author":"Farrukh Naveed Anjum","twitter_card":"summary_large_image","twitter_description":"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.","twitter_image":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/10\/Bert-Model.jpg","twitter_misc":{"Written by":"Farrukh Naveed Anjum","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/#article","isPartOf":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/"},"author":{"name":"Farrukh Naveed Anjum","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29"},"headline":"Understanding the BERT Model","datePublished":"2023-10-24T18:02:54+00:00","dateModified":"2023-10-24T18:02:56+00:00","mainEntityOfPage":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/"},"wordCount":474,"publisher":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization"},"keywords":["AI","BERT","Python"],"articleSection":["AI"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/","url":"https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/","name":"Understanding the BERT Model - Farrukh's Tech Space","isPartOf":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#website"},"datePublished":"2023-10-24T18:02:54+00:00","dateModified":"2023-10-24T18:02:56+00:00","description":"BERT (Bidirectional Encoder Representations from Transformers) revolutionized NLP by providing deep bidirectional text representations. Built on the Transformer architecture, BERT is pre-trained on massive data and fine-tuned for specific tasks. Python's transformers library offers straightforward BERT implementations for tasks like tokenization and classification.","inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/farrukhnaveed.co\/blogs\/understanding-the-bert-model\/"]}]},{"@type":"WebSite","@id":"https:\/\/farrukhnaveed.co\/blogs\/#website","url":"https:\/\/farrukhnaveed.co\/blogs\/","name":"Farrukh Naveed Anjum Blogs","description":"Empowering Software Architects with Knowledge on Big Data and AI","publisher":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/farrukhnaveed.co\/blogs\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/farrukhnaveed.co\/blogs\/#organization","name":"Farrukh Naveed Anjum Blogs","url":"https:\/\/farrukhnaveed.co\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg","contentUrl":"https:\/\/farrukhnaveed.co\/blogs\/wp-content\/uploads\/2023\/06\/IMG_5018-scaled.jpg","width":1707,"height":2560,"caption":"Farrukh Naveed Anjum Blogs"},"image":{"@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/ce7d07e6a917b9b73aa79007a2357d29","name":"Farrukh Naveed Anjum","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/farrukhnaveed.co\/blogs\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/bdf1af0d569259df562434e6dc99415a377c6fc053f9e1507aa34a6522561bb8?s=96&d=mm&r=g","caption":"Farrukh Naveed Anjum"},"description":"Full Stack Developer and Software Architect with 14 years of experience in various domains, including Enterprise Resource Planning, Data Retrieval, Web Scraping, Real-Time Analytics, Cybersecurity, NLP, ED-Tech, and B2B Price Comparison","sameAs":["https:\/\/farrukhnaveed.co\/blog"],"url":"https:\/\/farrukhnaveed.co\/blogs\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/203","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/comments?post=203"}],"version-history":[{"count":1,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/203\/revisions"}],"predecessor-version":[{"id":205,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/posts\/203\/revisions\/205"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/media\/204"}],"wp:attachment":[{"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/media?parent=203"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/categories?post=203"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/farrukhnaveed.co\/blogs\/wp-json\/wp\/v2\/tags?post=203"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}