Textkernel’s resume parsing (CV parsing) software Extract! automatically processes all your candidate data with the highest accuracy with no data entry required from you or your candidates. Textkernel’s software captures applications from your (mobile) career site, job boards, and your email inboxes to structure and enrich the information so it can be easily retrieved later. This will save you time and money on manually entering data.

Learn More

Textkernel Extract!CV/Resume Parsing Software

  • Save time on manual data entry
  • Collect applications from different sources
  • Structure information in Bullhorn
  • Increase the number of applicants
  • Easily grow your database

Automatic Resume Processing: Capture Candidate Data

With Extract! resume parsing, you can have resumes in multiple languages processed automatically with the highest accuracy, with no data entry required. Textkernel’s software structures and enriches the information so it can be easily retrieved later. This will save you time and money on manually entering data.

Candidate Inbox: Monitor Incoming Resumes

In the Candidate Inbox, you have all resumes in one easy-to-use central location. You can monitor the number of incoming resumes per day, see their status, check or add information to the individual resume via split screens, check for duplicates, and then save the information in Bullhorn.

Apply-with Widget

Offer your candidates a one-click (mobile) application process with Textkernel’s Apply-with widget. With this widget, your candidates can easily upload their resume, access it via the cloud or use a social media profile to apply with just a few clicks. You will automatically receive their information in Bullhorn and easily grow your talent pool.

Additional Features & Benefits

Multilingual resume processing

Textkernel is known for its multilingualism. With over 16 years of experience in multi-lingual resume parsing, Textkernel can parse complete resumes in over 17 languages: Dutch, English, German, French, Spanish, Swedish, Danish, Polish, Romanian, Italian, Slovak, Czech, Russian, Portuguese, Chinese, Hungarian and Greek and many more to come.

Full data model extraction

Extract! resume parsing accurately identifies and extracts all information from each resume. These fields include personal data, education (including qualifications, training and courses), work experience (including projects), languages, IT skills and soft skills, references and hobbies. It can also capture additional information and other metadata from the application process.

Mobile one-click apply

With Textkernel’s Apply-with widget connected to your Bullhorn system, your candidates can apply in just a few clicks with their resume or social media profile, even via their mobile. This fits perfectly in your mobile application process and you still receive all information structured in your Bullhorn database.

Normalization and ontologies

Extract! resume parsing can map extracted values to (hierarchical) taxonomies. One of our key strengths is to quickly build custom taxonomies for specific clients or industries. We also offer standard taxonomies. Besides mapping extracted values to taxonomies and standard skills, Extract! is also able to do fuzzy lookups in the resume texts for predetermined domain- or industry-specific lists of skills.

E-mail Parsing

With Textkernel’s Extract! you can manage your entire candidate workflow process, including automatic monitoring of e-mail boxes for applications, easily link your website to your Bullhorn system, automatically distribute applications to the right people in your organization and deduplicate incoming candidates against your Bullhorn candidates.

Highly accurate extraction powered by AI

Textkernel’s extensive knowledge of the HR field coupled with its specialization in cutting-edge AI and Machine Learning technologies make Extract! the most accurate parser on the market. Textkernel’s quality team routinely monitors the accuracy of the parsers and its research engineers are constantly working to further improve the performance of the various language models.

Learn More