Natural Language Processing combats manual text analysis

Thema:
Artifical intelligence

We’re constantly collecting more data, for example from camera images and text documents. This can provide us with relevant information. However, data is not always stored in a structured manner. This makes it difficult to retrieve the relevant information. Natural Language Processing (NLP) is an AI technique that tackles this problem.

What is natural language processing?

NLP combines the techniques of statistics with machine learning. This makes it possible to extract keywords from a text. We can then use this to make important classifications. TNO uses NLP to extract information from extensive, unstructured textual data in a more automated way.

TNO automatically creates taxonomies with natural language processing

You can use jargon to better streamline and standardise processes, for example in the form of a taxonomy or ontology. However, matching jargon within a field is a time-consuming exercise.

TNO uses NLP to identify important terms from a set of documents and determine their mutual relationships. We do this by:

  • combining syntactic information (sentence construction)
  • keyword extraction
  • web sources
  • semantic embedding methods

The taxonomy can then be used as input for an expert session.

Natural language processing is relevant for trend prediction

At TNO, we use our tools to automatically extract information from documents. We can also make predictions, such as in the foresight domain. Using the Horizon Scanner, we explore and extract from relevant websites, blogs and documents. This allows us to retrieve relevant information and to show trends.

Trend analysis shows us that the term deep learning is now being mentioned much more frequently within the computer vision domain than it was ten years ago. In addition, we can classify the documents automatically. For example, by a particular topic or field. We can also use blogs to conduct sentiment analysis and find out whether terms are being described more positively or negatively.

Get inspired

21 resultaten, getoond 6 t/m 10

Deep vision

Informatietype:
Article

Through Deep Vision, we’re developing AI algorithms to make automatic image analysis possible. Learn more!

Subsidence monitoring

Informatietype:
Article

The ground in the Netherlands is sinking. TNO is developing an AI model that will show which human activities contribute most to subsidence.

Predictive AI will soon make preventive healthcare possible

Informatietype:
Article

Predicting, based on health data, how likely it is that someone will get a particular disease or disorder. AI makes this possible in a safe way.

Fair decision making in the job market

Informatietype:
Article

Together with experts from the UWV, CBS and the Bureau for Economic Policy Analysis, TNO has shown in 2020 that AI can contribute to fair matchmaking.

Innovation monitoring in policy with AI

Informatietype:
Article

Identifying innovation trends faster? TNO, CBS and Innovatiespotter are currently researching new AI techniques to be used for this purpose.