{"id":76697,"date":"2025-12-12T08:22:31","date_gmt":"2025-12-12T07:22:31","guid":{"rendered":"https:\/\/oracioncristiana.org\/en\/ner\/"},"modified":"2025-12-12T08:22:31","modified_gmt":"2025-12-12T07:22:31","slug":"ner","status":"publish","type":"post","link":"https:\/\/oracioncristiana.org\/en\/ner\/","title":{"rendered":"Ner: the essential, practical guide with 7 key steps for NLP projects"},"content":{"rendered":"<h2><span class=\"ez-toc-section\" id=\"ner_explained_a_friendly_practical_guide_to_named_entity_recognition\"><\/span>ner explained: a friendly, practical guide to named entity recognition<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>In simple terms, ner is a way for computers to spot real\u2011world things mentioned in text: people, places, organisations, dates, products, and more. If you have ever searched your emails for a person\u2019s name, had a news app group stories about the same company, or seen a chatbot understand \u201cbook me a table on Friday\u201d, you\u2019ve benefited from ner. It sits at the heart of modern natural language processing, turning messy sentences into structured data that software can store, search, and act upon.<\/p>\n<p>This guide demystifies ner for non\u2011experts. We will explain what it is, where it helps, how it works under the bonnet, and what to watch out for. You will see practical examples, common pitfalls, and sensible steps to get started, whether you are exploring a hobby project or planning a business pilot.<\/p>\n<p>We keep the focus on clarity, not hype. You will meet just enough terminology\u2014such as \u201centities\u201d, \u201clabels\u201d, and \u201ctraining data\u201d\u2014to feel confident reading product pages or discussing options with a vendor. Along the way we\u2019ll point to trusted resources for deeper learning.<\/p>\n<p>By the end, you should understand why ner is important, how to evaluate it fairly, and what good practice looks like when you put an entity recognition system into production.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"What_is_ner_The_essentials\"><\/span>What is ner? The essentials<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Named entity recognition (often shortened to ner) is the task of automatically identifying spans of text that refer to specific things, and assigning them a category. For example, in \u201cRishi Sunak visited Manchester on Tuesday\u201d, a system might label \u201cRishi Sunak\u201d as a PERSON, \u201cManchester\u201d as a GPE (geo\u2011political entity), and \u201cTuesday\u201d as a DATE. The output is typically a list of entities with their text positions and types, turning unstructured words into a structured record.<\/p>\n<p>At its best, ner helps you:<\/p>\n<ul>\n<li>Search and organise large text collections by people, places, and topics.<\/li>\n<li>Automate compliance checks (e.g., flagging mentions of regulated organisations).<\/li>\n<li>Enrich customer support logs to identify recurring issues and named products.<\/li>\n<li>Power downstream analytics, such as knowledge graphs and relationship extraction.<\/li>\n<\/ul>\n<p>Some systems use a fixed set of categories (PERSON, ORG, DATE, MONEY, etc.), while others support custom labels for your domain, like MEDICATION in healthcare or CONTRACT_CLAUSE in legal work. The flexibility is a big reason ner is widely useful.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"How_ner_works_from_text_to_entities\"><\/span>How ner works: from text to entities<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Under the hood, there are three broad approaches to ner: rule\u2011based, machine\u2011learned, and deep learning with transformer models. Many practical solutions mix these methods.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Rule%E2%80%91based_approaches\"><\/span>Rule\u2011based approaches<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Rule\u2011based ner uses patterns and dictionaries to match entities. For example, you might write rules such as \u201ctwo capitalised words are likely a PERSON\u201d or maintain a gazetteer (a curated list) of city names. Rule\u2011based ner is fast and transparent, and it works well for predictable formats (like postcodes) or where you have excellent lists (like known product IDs). However, it struggles with unexpected phrasing and can be hard to maintain as language evolves.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Classical_machine_learning\"><\/span>Classical machine learning<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Statistical models\u2014such as Conditional Random Fields (CRFs)\u2014learn from annotated examples. You feed them sentences where humans have marked the entities, and the models learn patterns of characters, words, and parts of speech. Classical machine\u2011learning ner often performs strongly with modest training data and can be efficient, though it may miss complex context that modern deep models capture.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Deep_learning_with_transformers\"><\/span>Deep learning with transformers<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Today, transformer\u2011based models (for example, BERT and its variants) often deliver state\u2011of\u2011the\u2011art results on ner. They learn contextual representations of words, handling tricky phenomena like ambiguity (\u201cApple\u201d the company vs the fruit) by considering surrounding words. These models can be fine\u2011tuned on your labelled data to recognise custom entities. The trade\u2011off is that they require more compute, careful training, and thoughtful evaluation to avoid overfitting.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Common_entity_types_in_ner\"><\/span>Common entity types in ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>While you can define your own categories, many ner tasks use a core set of types. Understanding these helps you design sensible label sets:<\/p>\n<ul>\n<li>PERSON: names of people (e.g., \u201cAngela Merkel\u201d).<\/li>\n<li>ORG: companies, agencies, institutions (e.g., \u201cBBC\u201d, \u201cUnited Nations\u201d).<\/li>\n<li>GPE and LOC: countries, cities, regions, and general locations (e.g., \u201cKenya\u201d, \u201cCornwall\u201d).<\/li>\n<li>DATE and TIME: calendar dates and times (e.g., \u201c3 May 2026\u201d, \u201chalf past nine\u201d).<\/li>\n<li>MONEY and PERCENT: monetary amounts and percentages (e.g., \u201c\u00a32.3m\u201d, \u201c15%\u201d).<\/li>\n<li>PRODUCT, WORK_OF_ART, EVENT: manufactured items, creative works, and named events (e.g., \u201ciPhone 15\u201d, \u201cHamlet\u201d, \u201cCOP28\u201d).<\/li>\n<\/ul>\n<p>For specialised domains, it is common to add labels like CHEMICAL, DISEASE, CASE_LAW, or INGREDIENT. Good ner design balances usefulness with labelling cost: too many labels increase complexity and reduce consistency.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Practical_uses_of_ner\"><\/span>Practical uses of ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Because it converts text into structured data, ner supports many real\u2011world tasks:<\/p>\n<ul>\n<li>News and media: tag articles by people and organisations to improve recommendations and topic pages.<\/li>\n<li>Customer support: pull out product names, error codes, and dates to speed triage and reporting.<\/li>\n<li>Compliance and risk: detect mentions of sanctioned entities, sensitive projects, or locations.<\/li>\n<li>Healthcare: extract medications and dosages (with strict privacy safeguards) from clinical notes.<\/li>\n<li>Legal and finance: surface counterparties, contract terms, and monetary amounts from documents.<\/li>\n<li>Research and archives: index historical texts by names and places to make collections searchable.<\/li>\n<\/ul>\n<p>As a concrete illustration, consider long religious texts or translations where language varies across editions. When applying ner to complex passages\u2014such as <a href=\"https:\/\/oracioncristiana.org\/en\/longest-verse-in-the-bible\/\">the longest verse in the Bible<\/a>\u2014you face nested names, archaic terms, and culturally specific references. This is where domain adaptation and careful guidelines matter.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Implementing_ner_step_by_step\"><\/span>Implementing ner step by step<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p><\/p>\n<div id='video-container' data-video-id='4rsPcCjMk1o' style='width:100%; height:auto; max-width:587px; position: relative;'>\n<div class='image-video-plugin' style='background:url(\"https:\/\/img.youtube.com\/vi\/4rsPcCjMk1o\/0.jpg\") center no-repeat; background-size: cover;'><\/div>\n<p>        <span class='youtube-play-button'><\/span><br \/>\n        <noscript><a href=\"https:\/\/www.youtube.com\/watch?v=4rsPcCjMk1o\" target=\"_blank\" rel=\"noopener\"><\/a><\/noscript>\n    <\/div>\n<p><\/p>\n<p>If you plan a small project or pilot, here is a sensible path to follow:<\/p>\n<ol>\n<li>Define the goal. Decide which entities you truly need and how you will use them. Keep labels few and useful.<\/li>\n<li>Assemble data. Gather representative texts. Ensure coverage of different styles (emails, reports, transcripts) if relevant.<\/li>\n<li>Write labelling guidelines. Specify what counts as an entity and how to handle tricky cases (hyphenation, titles, nested mentions).<\/li>\n<li>Annotate a sample. Label a small set carefully with two people to measure agreement. Refine guidelines based on disagreements.<\/li>\n<li>Choose a baseline. Start with an off\u2011the\u2011shelf ner model (e.g., English general model) and test on your data to set a benchmark.<\/li>\n<li>Fine\u2011tune or customise. Train on your annotations; optionally add rule\u2011based post\u2011processing for business\u2011specific corrections.<\/li>\n<li>Evaluate properly. Use a held\u2011out test set. Report precision, recall, and F1 at the entity level and by label.<\/li>\n<li>Deploy and monitor. Start small, collect feedback, and watch performance over time. Update the model when data shifts.<\/li>\n<\/ol>\n<p>Vocabulary choices can influence recognition. If you rely on gazetteers or synonyms to broaden coverage, make sure your lists match how people actually write. For instance, when curating alternatives to common adjectives, tools that explore synonyms\u2014such as a page of <a href=\"https:\/\/oracioncristiana.org\/en\/numerous-synonym\/\">synonyms for numerous<\/a>\u2014can remind you how varied everyday language can be. Variety in your training examples helps ner handle that real\u2011world diversity.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Quality_metrics_and_evaluation_in_ner\"><\/span>Quality, metrics, and evaluation in ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Measuring ner fairly avoids surprises later. Three core metrics matter:<\/p>\n<ul>\n<li>Precision: of the entities the system predicted, how many were correct?<\/li>\n<li>Recall: of the true entities present, how many did the system find?<\/li>\n<li>F1: the harmonic mean of precision and recall, balancing both.<\/li>\n<\/ul>\n<p>Important details:<\/p>\n<ul>\n<li>Entity\u2011level scoring: a prediction must have the correct span and label to count as correct. Token\u2011level accuracy can be misleading.<\/li>\n<li>By\u2011label breakdown: overall F1 can hide weak labels (e.g., great on PERSON, poor on PRODUCT). Inspect each category.<\/li>\n<li>Cross\u2011domain tests: if you will process emails and PDFs, evaluate on both. Domain shift is a common cause of ner failures.<\/li>\n<li>Confidence thresholds: many models output scores. Calibrate thresholds to trade precision against recall depending on the use case.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Challenges_and_common_mistakes_with_ner\"><\/span>Challenges and common mistakes with ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Even robust systems have rough edges. Watch for these issues:<\/p>\n<ul>\n<li>Ambiguity: \u201cAmazon\u201d could be a company or a river. Add context in training data and, where helpful, follow ner with disambiguation rules.<\/li>\n<li>Nested and overlapping entities: \u201cUniversity of Oxford Medical School\u201d contains an organisation within another. Standard ner schemes often forbid overlaps; decide your policy early.<\/li>\n<li>Annotation inconsistency: if annotators disagree, models learn noise. Invest in clear guidelines and quality checks.<\/li>\n<li>Imbalanced labels: rare categories (like WORK_OF_ART) need extra examples or targeted augmentation.<\/li>\n<li>Text normalisation: quirky punctuation, OCR errors, and encoding issues can break tokenisation and harm ner performance.<\/li>\n<li>Privacy and ethics: extracting personal data has legal and ethical implications. Minimise, secure, and audit usage.<\/li>\n<li>Overfitting: dazzling results on your training set but weak generalisation. Keep a clean test set and validate regularly.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Best_practices_for_production%E2%80%91grade_ner\"><\/span>Best practices for production\u2011grade ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>For systems that people rely on, treat ner as a product, not a one\u2011off model:<\/p>\n<ul>\n<li>Data governance: document sources, consent, retention, and sharing policies. Respect data minimisation.<\/li>\n<li>Human oversight: enable users to correct entities. Use feedback to improve future versions.<\/li>\n<li>Monitoring: track metrics by label and input source. Set alerts for drift and performance drops.<\/li>\n<li>Versioning: version data, models, and configurations so you can reproduce results and roll back safely.<\/li>\n<li>Security: restrict access to sensitive outputs (e.g., personal names) and log who views what.<\/li>\n<li>Accessibility: design outputs that non\u2011experts can understand, with clear labels and links back to the source text.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Examples_a_tiny_ner_project_in_practice\"><\/span>Examples: a tiny ner project in practice<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Imagine you work in a small publisher and want to tag articles with people and places to improve your website\u2019s search. Here is a pragmatic plan:<\/p>\n<ul>\n<li>Collect 500 articles from the past year, ensuring a mix of topics and styles.<\/li>\n<li>Choose labels PERSON and GPE to start. Keep it simple.<\/li>\n<li>Annotate 150 articles with two colleagues. Agree how to handle titles (\u201cDr\u201d, \u201cSir\u201d) and multi\u2011word places.<\/li>\n<li>Fine\u2011tune an English transformer model on 120 articles; keep 30 for testing.<\/li>\n<li>Evaluate: aim for F1 above 85% on both labels. Review top errors (missed hyphenated names, regional towns).<\/li>\n<li>Deploy: run ner on your back catalogue, store entities in your CMS, and add filters like \u201cPeople mentioned\u201d.<\/li>\n<li>Iterate: every quarter, label 50 new articles from emerging topics and refresh the model.<\/li>\n<\/ul>\n<p>If you plan to expand into cultural or religious history pieces, build a small domain lexicon\u2014say, archaic place names or alternative spellings\u2014to complement ner predictions. When texts are dense or unusually structured, as with very long verses or ceremonial titles, using examples like <a href=\"https:\/\/oracioncristiana.org\/en\/longest-verse-in-the-bible\/\">the longest verse in the Bible<\/a> during evaluation can reveal edge cases you might otherwise miss.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Recommended_external_resources\"><\/span>Recommended external resources<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/en.wikipedia.org\/wiki\/Named-entity_recognition\" target=\"_blank\" rel=\"noopener\">Wikipedia overview of named entity recognition<\/a> for a broad, neutral introduction to the task and its history.<\/li>\n<li><a href=\"https:\/\/spacy.io\/usage\/linguistic-features#named-entities\" target=\"_blank\" rel=\"noopener\">spaCy guide to named entities<\/a> for practical tips, examples, and pipeline configuration.<\/li>\n<li><a href=\"https:\/\/nlp.stanford.edu\/software\/CRF-NER.html\" target=\"_blank\" rel=\"noopener\">Stanford CRF\u2011NER software<\/a> for a classical machine\u2011learning baseline and long\u2011standing documentation.<\/li>\n<li><a href=\"https:\/\/huggingface.co\/docs\/transformers\/tasks\/token_classification\" target=\"_blank\" rel=\"noopener\">Hugging Face tutorial on token classification (NER)<\/a> to fine\u2011tune transformer models on your data.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Related_articles\"><\/span>Related articles<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/oracioncristiana.org\/en\/numerous-synonym\/\">synonyms for numerous<\/a><\/li>\n<li><a href=\"https:\/\/oracioncristiana.org\/en\/longest-verse-in-the-bible\/\">the longest verse in the Bible<\/a><\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Frequently_asked_questions_about_ner\"><\/span>Frequently asked questions about ner<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"Is_ner_the_same_as_entity_extraction\"><\/span>Is ner the same as entity extraction?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>The terms overlap and are often used interchangeably. Strictly speaking, ner refers to identifying and labelling named entities in text, while \u201centity extraction\u201d may also include linking entities to knowledge bases (\u201cParis\u201d the city vs the mythological figure) and pulling attributes. In everyday use, people often say ner for both.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"How_much_data_do_I_need_to_train_a_custom_ner_model\"><\/span>How much data do I need to train a custom ner model?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>It depends on your labels and how different your texts are from general English. As a rough guide, a few thousand labelled entities (not documents) can get you started for a simple two\u2011label system. If your domain is specialised or the language is noisy (OCR scans, social media), expect to need more examples and careful guidelines.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Can_I_use_ner_without_coding\"><\/span>Can I use ner without coding?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Yes. Many off\u2011the\u2011shelf tools and cloud services provide ner via point\u2011and\u2011click interfaces or simple APIs. For more control (custom labels, privacy), lightweight code using libraries like spaCy or Hugging Face is often manageable for non\u2011developers with some patience and good tutorials.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"What_languages_does_ner_support\"><\/span>What languages does ner support?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Modern models support many languages, but quality varies. High\u2011resource languages (English, Spanish) tend to have stronger models. For low\u2011resource languages, you may need to annotate your own data or adapt multilingual models. Always test on your actual text.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"How_do_I_handle_privacy_and_compliance_when_using_ner\"><\/span>How do I handle privacy and compliance when using ner?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>Treat extracted entities as sensitive if they include names, addresses, or health data.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_86 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title ez-toc-toggle\" style=\"cursor:pointer\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Alternar tabla de contenidos\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 eztoc-toggle-hide-by-default' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#ner_explained_a_friendly_practical_guide_to_named_entity_recognition\" >ner explained: a friendly, practical guide to named entity recognition<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#What_is_ner_The_essentials\" >What is ner? The essentials<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#How_ner_works_from_text_to_entities\" >How ner works: from text to entities<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Rule%E2%80%91based_approaches\" >Rule\u2011based approaches<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Classical_machine_learning\" >Classical machine learning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Deep_learning_with_transformers\" >Deep learning with transformers<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Common_entity_types_in_ner\" >Common entity types in ner<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Practical_uses_of_ner\" >Practical uses of ner<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Implementing_ner_step_by_step\" >Implementing ner step by step<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Quality_metrics_and_evaluation_in_ner\" >Quality, metrics, and evaluation in ner<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Challenges_and_common_mistakes_with_ner\" >Challenges and common mistakes with ner<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Best_practices_for_production%E2%80%91grade_ner\" >Best practices for production\u2011grade ner<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-13\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Examples_a_tiny_ner_project_in_practice\" >Examples: a tiny ner project in practice<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-14\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Recommended_external_resources\" >Recommended external resources<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-15\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Related_articles\" >Related articles<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-16\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Frequently_asked_questions_about_ner\" >Frequently asked questions about ner<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-17\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Is_ner_the_same_as_entity_extraction\" >Is ner the same as entity extraction?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-18\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#How_much_data_do_I_need_to_train_a_custom_ner_model\" >How much data do I need to train a custom ner model?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-19\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#Can_I_use_ner_without_coding\" >Can I use ner without coding?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-20\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#What_languages_does_ner_support\" >What languages does ner support?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-21\" href=\"https:\/\/oracioncristiana.org\/en\/ner\/#How_do_I_handle_privacy_and_compliance_when_using_ner\" >How do I handle privacy and compliance when using ner?<\/a><\/li><\/ul><\/li><\/ul><\/nav><\/div>\n","protected":false},"excerpt":{"rendered":"<p>ner explained: a friendly, practical guide to named entity recognition In simple terms, ner is a way for computers to spot real\u2011world things mentioned in text: people, places, organisations, dates, products, and more. If you have ever searched your emails for a person\u2019s name, had a news app group stories about the same company, or &hellip;<\/p>\n","protected":false},"author":2,"featured_media":76698,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-76697","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-chiristian"],"_links":{"self":[{"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/posts\/76697","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/comments?post=76697"}],"version-history":[{"count":0,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/posts\/76697\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/media\/76698"}],"wp:attachment":[{"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/media?parent=76697"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/categories?post=76697"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/oracioncristiana.org\/en\/wp-json\/wp\/v2\/tags?post=76697"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}