Self-Attentional Multi-Field Features Representation and Interaction Learning for Person–Job Fit

Person–job fit, which aims to predict the matching degree between a resume and a job, has become an effective way to overcome information overload in the recruitment market. Existing studies on person–job fit usually focus on the representation learning of textual data in jobs and resumes. Person–job fit is a highly nonlinear complex problem that is affected by several fields of features. We assume that it would bring benefits to comprehensively consider the numerical features, categorical features, and textual features of resumes and jobs. To this end, we propose a novel model based on the self-attention mechanism, named MUlti-Field Features representation and INteraction (MUFFIN) learning for person–job fit. The key idea is to explore meaningful feature representations and interactions. Specifically, we group all the features of resumes and jobs into several fields. And a module is introduced to learn the hidden vectors of feature correlations in each feature field. Along this line, we propose a module with the multi-head self-attention mechanism and a residual connection to further model the feature field interactions. Moreover, we utilize a multi-layer perceptron (MLP) to measure the matching score between a resume and a job. Finally, the experimental results on a real-world dataset validate the effectiveness of MUFFIN for person–job fit.