What is Resume Parsing and a Resume Parser?

In computer science, parsing is the process of analyzing an input sequence in order to determine its grammatical structure with respect to a given formal grammar. A parser is a computer program that carries out this task. In today’s world of ATS and Job Boards, a resume parser is a component that sits between the application and a database. Résumés in all formats and of all file types go in and structured data comes out; generally in XML or JSON format. During the process semantic analysis and rules are used to create hierarchies (trees) of competencies and skills to aid in precision of future database searches. Similarly, the same rules are used to create a set of competencies from job orders and vacancies. Doing so allows for more precise matching between job order and candidates.

HireAbility’s ALEX (Automated Linguistics EXpert) is a resume parser that uses pattern recognition, language structure, and artificial intelligence to extract the content of a résumé (CV) or a job order (vacancy) into a predefined format (e.g. HR-XML, JSON) described above.

The data extracted and tagged includes but is not limited to the person’s name and contact information, employment history, education, skills and competencies, publications, awards, licenses and certifications, associations, security clearances, references, citizenship, etc. The parser is a context-based tool. Because of it the parser is able to structure the most unconventional resumes. Thus the parser practically eliminates any chance of someone searching for Oracle as a skill ending up finding candidates who work at Oracle but have no Oracle skills.

In addition HireAbility’s ALEX creates a summary of extracted data such as the 3 most relevant competencies (most used over the years), the most recent company where the candidate worked, competencies and skills used in the last job, highest level of education, number of years in management positions, years of experience and many more.

Using the parser to structure resume data drastically impacts searching and display capabilities of an application.