Resume Parsing based on Multi-label Classification using Neural Network models

• DOI: 10.1145/3469968.3469998
• Publication Date: 2021-10-06T22:21:24Z
• Authors: Jiahao Liu; Yifan Shen; Yijie Zhang; Sujatha krishnamo...
• Keywords: Multi-label classification

Application for jobs usually brings much work both appliers and HR. Appliers want to apply the which they are most suitable. The number of applications a particular position can be significant, making candidates' selection cumbersome Nowadays, hiring processes often conducted through Virtual mode with emails. This creates chances analyzing data in resume. Therefore, enhance problems' efficiency, resume parsing algorithms have been developed recent years predict resume-based skills or good quickly. artificial neural network is hot spot field intelligence since 1980s. It abstracts human brain's from angle information processing, establishes some simple models, forms different networks according connection modes. In years, networks-based perform high efficiency processing text classification. paper put forward efficient used classification, Like BPNN, CNN, BiLSTM, CRNN, parsing. original resumes parsed by splitting them into words, word base trained get appropriate word, has score resulting suitable job each CRNN performs best parsing, accuracy reach 96%. CNN places lowest accuracy. BPNN achieves but inflexible.