Last month, Textkernel introduced two new language models for CV parsing: Russian and Portuguese. This brings the total number of languages offered by Textkernel to 14. Russian and Portuguese are included in the new release of Extract! resume parsing and are already available. If you would like more information about this, contact us language models. Besides from the introduction of the new language models, several new and improved features have been added:
- New: page classifier for German OCR resumes. The software can now identify all separate pages of the document as being part of the resume or not
- New: Czech education level extraction from the education section
- Improved Czech extraction model
- Improved processing of Czech RTF documents
- Improved extraction of German and Dutch education levels from the education sections
- Improved French-Canadian address extraction
Do you want to know more about this new release? Ask for a free demo.