igital information is becoming more and more abundant in all areas, for example news are today available in many different languages from various sources. Other examples are business systems that today are consolidated and integrated and, therefore, produce a lot of unstructured data, for example medical patient records. How can we process this information so we can easily navigate through it? Can we present it in a way that is easily understandable? Can we also extract gold nuggets with information that is not visible for the bare eye?
These are some of the research queries we are treating in our research in human language technology, using automatic summarization of text, named entity recognition, cross language information retrieval, text clustering, and text- and data mining.
Please do not hesitate to contact Dr. Hercules Dalianis if you have any questions around this area.
Try our Automatic text summarizer, SweSum.
Read more about our research project Knowledge Extraction Agent.