Published: April 10, 2020. This article is part of the Introduction to Natural Language Processing Learning Program.
As shown in the previous demonstration, with the natural language processing capabilities of IBM® Watson ™, you can efficiently analyze large amounts of text to produce actionable insights. Provide Watson with a URL or a popular news site, and Watson will be able to receive the source text and analyze it in seconds, much faster than a human. The text is analyzed by categories, concepts, emotions, entities, relationships, feelings and much more, options that you can customize. The information extracted from this service allows you to find more meaning in the text, understand trends and recommend similar content from large amounts of data.
This article explains how IBM Watson can help you use natural language processing services to develop increasingly intelligent applications. While you focus primarily on Watson Natural Language Understanding and Watson Knowledge Studio services, you can learn about Watson Discovery through the Watson Discovery learning path.
Take a look at a quick demo to see the skills of the Watson Natural Language Understanding service.
Watson Natural Understanding specific terms
Natural language processing is a subfield of linguistics, computer science and artificial intelligence that studies the interaction between computers and human languages; more specifically, how to program computers to process and analyze large amounts of natural language data. This section explains terms that are specific to Watson Natural Language Understanding.
Natural Language Understanding: a subtopic of natural language processing in AI that deals with how machines interpret text and understand meanings based on context.
Resources: the possible classifications that Watson Natural Language Understanding is capable of producing from the text input provided. This includes categories, concepts, emotions, keywords, metadata, relationships, semantic functions and feeling.
Entities: people, companies, location and ratings made by Watson. A complete list of entity types and subtypes can be found in the Natural Language Understanding documentation.
Categories: five levels of hierarchies that Watson can identify from the input text. The following is an example for a “fax machine”.
Level 1 – technology and computing
Level 2 – hardware
Level 3 – computer peripherals
Level 4 – printers, copiers and faxes
Level 5 – fax machines
Concepts: high-level concepts that are not necessarily referenced directly in the text.
Metadata: A data set that describes and provides information about other data. For example, for a given input URL, metadata fields can include publication date, title and author.
Relationships: the recognition of when two entities are related and the identification of the type of relationship.