Resume Parser: Semi-structured Chinese Document Analysis

摘要

Semi-structured Chinese document analysis is the most difficult task for complex structure and Chinese semantics. According to the generic characteristics of the semi-structured document and the specific characteristics of the resume document, the paper researched on resume document block analysis based on pattern matching, multi-level information identification and feedback control algorithms was also prompted. Based on the research, resume parser system was implemented for ChinaHR, which is the biggest recruitment Website. It can read, analysis, retrieval and store the information automatically. According to all kinds of experiments results, the accuracy and efficiency of this system can generally satisfy the practical requirements. As the research on the processing of the semi-structured document, it will not only be as a directive of the further research on the resume analysis, but also be as the reference to other form of the semi-structured document.