Back to all updates

5 months ago

NL API Cheat Sheet

As you work with the NL API, we thought it might be helpful to give you a quick cheat sheet to familiarize yourself with the main components.  One of the best and easiest ways to test the results of our NL API is to use our demo site:


Select a sample document or copy and paste up to 10,000 characters to be analyzed by the API. Once done, you can easily review how the API understands the piece of text in various ways.  With each of the endpoints and features mentioned below, you can also choose to view the JSON which is how the results will look returned from the engine.  Here is a quick cheat sheet of features you’ll see in the results:

  • Disambiguation: The result of deep linguistic analysis including detailed syntax identifying tokens, part-of-speech tags, phrases, sentences, full dependency tree, and concept labels. Learn more.
  • Main Elements & Topics: Key lemmas, phrases, knowledge graph concepts (here called Syncons), sentences and knowledge graph topics found in the text, each with its relevance score. Learn more.
  • Named Entities: People, organizations, places, and values (such as currency amounts, percentages and measures) mentioned in the text, with the corresponding links to open data sources such as Wikidata, DBpedia and GeoNames. Learn more.
  • Classification: Labels the document according to one of four included taxonomies: IPTC Media Topics, GeoTax, Emotional Traits or Behavioral Traits. Learn more.
  • Relations: The semantic role of predicative expressions, attributes, adjuncts and subordinate clauses that precede or follow a verb. Relations show the subject and the object of verbs and help answer questions like: "who did what when?", "what caused what to whom?", etc. Learn more.
  • Sentiment: How positive or negative the tone of a text is. It takes into account the intrinsic positivity or negativity of the concepts expressed in the text and the relationships between the concepts and other elements of the text, such as negations. Learn more.
  • Writeprint: Performs a stylometric analysis of the documents, ranging from readability and vocabulary richness to verb types, document structure and grammar. Learn more.
  • PII Detection: Identifies personally identifiable information in text. Learn more.



If you have any questions about the hackathon, please post on the developer community.