This is the most comprehensive and intuitively simple tool I have ever worked with. Particularly important for me was the time spent on matching employees to the offers, which Element does for me.
One of the basic applications of artificial intelligence in our ATS is to support recruitment processes by automating time-consuming and costly activities that make up the entire recruitment process. There three goals that we have for artificial intelligence, which we develop in Element recruitment system:
In the previous blog post, we discussed how artificial intelligence allows us to parse CVs and how this technology is revolutionizing the way we work with large databases of candidates. In this article, I will tell you how we developed our AI and how we are teaching it to parse more complicated CVs.
As mentioned above, in our last blog post, we have explained how CV parsing works. In a nutshell, it comprises reading CV’s content and deciding which part is the first name, last name, job position, employment start and end dates, university degree, ability, etc.
But how artificial intelligence is supposed to know the meaning behind words and numbers present in the document? How AI knows that „John” is a name, and „Java Developer” is a job position?
We have to teach it. How does one teach artificial intelligence? It is more or less the same process as teaching a child how to read. But before we started teaching it, we first had to plan our child and then give birth to it.
The first and fundamental challenge we faced many months ago was the fact that artificial intelligence in recruitment systems is a new and not very well developed technology. We didn’t have too many sources of knowledge or data resources to use in our work. We started almost from scratch.
In the first place, we found a dozen scientific papers that concerned the application of artificial intelligence to the analysis of text and CV content. After analyzing all the sources of knowledge available to us, however, we decided that the best solution would be to take all the best of the current knowledge, add our own ideas and create an entirely new solution. After many days of analyses and plans, we made the necessary decisions related to the preparation of infrastructure and neural networks on which we will base our artificial intelligence. Next, we just needed the data.
As I mentioned, the development of artificial intelligence is like teaching a child. In both cases, teaching is a long-term process. In the case of artificial intelligence, the purpose of which is to parse CVs, teaching consists of providing a large number (counted in thousands) of specially prepared CVs. These specially prepared CVs are documents, created in a separate module of our ATS, in which we tag individual parts of the content, and then assign appropriate meaning to these parts. This process of preparing CV goes like this: we read the content of the CV. When we come across the word Maciej, I tag this word as a name. If I find a date, then I tag this date as, e.g., starting a specific position in a particular company. This way, we go through the entire CV and tag each phrase in it. The process is very similar to completing a Linkedin profile.
It may seem simple at first sight. In fact, it is full of traps, ambiguities, and the need to make compromises. One of the permanent elements of the development of artificial intelligence in ATS Element are regular sessions during which we analyze the progress of work. During these sessions, we also try to solve problematic situations related to data tagging. Here are some examples:
The more CVs, the more such questions we need to answer. Human creativity is limitless, and it is impossible to create a single algorithm that will correctly parse every type of CV. This is why artificial intelligence is used to solve such difficult problems. But to teach AI to cope with the limitless diversity of human creativity, we need to provide it with many thousands of carefully prepared examples. These examples are meant to show AI how human intelligence solves such problems.
How does artificial intelligence learn from these examples? Well, for AI this is just a matter of statistics. If the algorithm receives 10,000 examples, in which two words in the first two lines of the document will be tagged as first and last name, then in document number 10,001 it will find a similar pair of words on its own and correctly indicate which of them is the first and which is the last name. It is important to understand that this is not a matter of simply „remembering” the first and last names. Artificial intelligence does not remember the meanings of words, but each time it decides on the meaning of a word, assessing the context of its use and its location throughout the document.
It will probably take many years, maybe decades, before anyone creates artificial intelligence that can flawlessly interpret CVs. Human creativity is limitless; new concepts and words appear; old ones change their meanings over time. Just as a person is not able to solve every problem, neither will artificial intelligence. However, we do not expect perfection. One of the primary goals of AI in our recruitment system is to automate simple but time-consuming and costly processes such as CV parsing. Every part of the CV content that has been correctly interpreted by our ATS saves recruiters valuable seconds of work. These seconds are what we fight for. From these seconds, we build the minutes, which we then convert into hours of cost savings.
hashtags# Artificial Intelligence ATS Recruitment System Element
We bring positive signals from the labor market! Check an update of Grant Thornton and Element ATS recruitment report.
What are the recruitment needs of particular industries in April 2020? Check an update of Element ATS recruitment report.
Recruiter Magazine report on recruitment in the Polish IT industry. Our ATS have provided data for the report. We also share the latest data from the recruitment market.