
We are excited to share with you an overview of Textkernel’s latest and upcoming updates for our CV parsing solution Extract! and our Skills API.
CV parsing in Hebrew – and very soon in Traditional Chinese
We’ve just added our 24th CV parsing language: Hebrew! Being written from right to left, it’s surely one of the more challenging languages. Nevertheless, we’ve managed to achieve a very high level of accuracy, similar to our best-performing languages. Customers who are expecting to parse Hebrew CVs can contact their account manager in order to activate it in their account.
And that’s not all: the next two languages are already in the making. In Q3 2022, we’re expecting to add Traditional Chinese.
Improvements for Portuguese CV Parsing and other languages
The Portuguese CV parser was upgraded with our Deep Learning Technology. This resulted in major accuracy improvements of 40 to 80%, depending on the field. We have also improved the recognition of locations (addresses and regions) for CVs from Colombia and Brazil. And as always, we’ve made many smaller improvements to the other parsing languages. Of course, users of the Extract API will automatically benefit from all of these improvements.
New languages in our Skills Taxonomy
Not only our CV parsing product keeps expanding. Our Skills Taxonomy is also growing internationally. It also supports Hebrew now, and in Q3 2022 we’re expecting support for Traditional Chinese, Portuguese and Japanese. More languages will follow shortly after.
What is the Skills Taxonomy? The Skills Taxonomy helps understanding the skills of your candidates and employees to make them better searchable and analyzable. The taxonomy is one of the core components of the Data Enrichment APIs and also embedded within our CV parser.
Do you want to learn more about our products or schedule a demo with one of our colleagues, please contact us!