Get more value out of unstructured data with IBM Watson Natural Language Understanding

Thibault Anderlin Cognitive Computing

Save time with out-of-the-box NLP models like named entity recognition, sentiment analysis, keyword extraction, and more – built and continuously improved upon by our teams of data scientists, machine learning engineers, and linguistics experts.

Watson provides a comprehensive suite of natural language processing capabilities through Watson Natural Language Understanding, Watson Discovery, and Watson Knowledge Studio.

Natural language processing (NLP) is the parsing and semantic interpretation of text, which allows systems to learn, analyze, and understand human language. With Watson’s suite of NLP offerings, including Watson Natural Language Understanding (NLU), you can surface concepts, categories, sentiment, and emotion, and apply knowledge of unique entities in your industry to your data, no matter where it lives.

Analyze text to extract metadata from content such as concepts, entities, keywords, categories, sentiment, emotion, relations, and semantic roles.



Extract metadata from unstructured text for deep analysis.

Content recommendation

Recommend similar content to what users are interested in viewing or experiencing.

Data mining

Search through large content repositories and quickly uncover relevant answers.

Powerful Insights

Engage with a full suite of advanced text analytics features to extract entities, relationships, keywords, semantic roles and more.

Domain Customization

Apply the knowledge of unique entities and relations in your industry or organization to your data.

Broad Language Coverage

Interpret text in thirteen different languages, with more on its way.

There are various use cases for Watson Natural Language Understanding. These include advertising optimization, content recommendation, voice-of-customer analysis, audience segmentation, data mining, and more. NLU allows for the extraction of insights from unstructured data.
All three products can be used independently of one another. Natural Language Understanding is a best-of-breed text analytics service that can be integrated into an existing data pipeline. Watson Discovery incorporates Natural Language Understanding, but also offers storage of data with multiple ingestion options and provides the opportunity of powerful queries to extract insights, serving as a powerful cloud native insight engine. Watson Knowledge Studio can be used with both Discovery and Natural Language Understanding to customize text extraction of entities and relations using machine learning models.
NLU supports 13 languages, depending on the feature: Arabic, Chinese (Simplified), Dutch, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish, Swedish and other new languages will be added frequently.

Natural language understanding features.


Categorize your content using a five-level classification hierarchy.


Identify high-level concepts that aren’t necessarily directly referenced in the text


Analyze emotion conveyed by specific target phrases or by the document as a whole.


Find people, places, events, and other types of entities mentioned in your content.


Search your content for relevant keywords.


Analyze the sentiment toward specific target phrases and the sentiment of the document as a whole.



For HTML and URL input, get the author of the webpage, the page title, and the publication date.


Recognize when two entities are related, and identify the type of relation.

Semantic Role

Parse sentences into subject-action-object form, and identify entities and keywords that are subjects or objects of an action.

Custom Models

Identify custom entities and relations unique to your domain with Watson Knowledge Studio.


Product Integrations.


Watson Knowledge Studio

Teach IBM Watson the language of your domain with custom models that identify entities and relationships unique to your industry in unstructured text. Build your models in a collaborative environment designed for both developers and domain experts, without needing to write code.
Learn more

Watson Discovery

Unlock hidden value in data to find answers, monitor trends, and surface patterns. It makes it easy to build AI solutions that find relevant answers in complex, disparate data with speed and accuracy. A new feature, smart document understanding, speeds training, enabling cleaner answers in less time with less effort.
Learn more

Watson Assistant

Quickly build and deploy virtual assistants across a variety of channels. it is an offering for building conversational interfaces into any application, device, or channel. Most chatbots try to mimic human interactions, which can frustrate users when a misunderstanding arises. Watson Assistant is more.
Learn more

Natural Language Understanding in action

Natural Language Understanding is a collection of APIs that offer text analysis through natural language processing. This set of APIs can analyze text to help you understand its concepts, entities, keywords, sentiment, and more. Additionally, you can create a custom model for some APIs to get specific results that are tailored to your domain

Discover it now

This demo shows how Watson Natural Language Understanding provides insights on unstructured data.

View the Demo