Image: OpenClipartVectors. Source: Pixabay.
The Australian online recruitment portal, The Search Party, is using machine learning and natural language algorithms to digitalise and scan 15 millions of resumes, informs the journal CIO in an article, which echoes Dail Software.
The algorithms scan resumes which belong to the same person in order to find differences. A candidate may have updated his or her resume in different moments and in various places, or may have created different resumes depending on the job.
The variables the algorithm looks at are full name, email address, names of companies a candidate has worked for, phone number(s) and list of skills sets.
The text is processed in a way that data turns into numerical vectorsFirst, the data is tokenised into text snippets. For example, the name Dylan is broken up into segments ‘dy, ‘yl’, ‘la’, and ‘an’. This makes it robust to spelling variations.
The algorithms scan resumes which belong to the same person in order to find differences. A candidate may have updated his or her resume in different moments and in various places, or may have created different resumes depending on the job.
The variables the algorithm looks at are full name, email address, names of companies a candidate has worked for, phone number(s) and list of skills sets.
The text is processed in a way that data turns into numerical vectorsFirst, the data is tokenised into text snippets. For example, the name Dylan is broken up into segments ‘dy, ‘yl’, ‘la’, and ‘an’. This makes it robust to spelling variations.
English
