Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

XTRACT

Reference number
Coordinator Textual Relations AB
Funding from Vinnova SEK 2 709 100
Project duration March 2018 - August 2019
Status Completed
Venture Eurostars

Purpose and goal

The purpose of the project is to apply the information extraction technology into two new products. "Assist" focussing on automation of customer support and "Construct" that uses product data to create product information for multiple channels and languages. The products are making existing processes more efficient aswell as enable a better customer experience. With this technology Textual now has an increased competitiveness.

Expected results and effects

Textual has identified great opportunities related to the developed technology. Both within existing Textual services becoming more scalable. Also, providing this as separate service. We are scaling the sales efforts and expect 100 new clients with this new platform during 2019-2020.

Planned approach and implementation

Within the project several different technologies where used to developed the extraction system. Information was extracted using different technologies depending on granularity and domains. Analyzing the process we see that many times the unstructured input data could be ungrammatical or incorrect. The trained algorithms may not handle this automatically. Since this is the nature of language, manual quality assurance may be needed in some cases.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 8 January 2019

Reference number 2018-00682

Page statistics