In this concluding week, I created the record structure for the xml data and ran my ECL file.
The record structure is critical as it serves as a repository of information of all the candidates that apply to a particular post. Resumes come as part of Big Data. Therefore by leveraging the HPCC Systems, large number of resumes can be processed and the information can be placed into a record which simplifies the process of filtering candidates. This is the output that is obtained:
This is the record that contains all the information of the different candidates and by specifying specific eligibility criteria, the candidates can be segregated accordingly which is the ultimate outcome of this project.
The project was overall, a very interesting one, but although it was challenging, the NLP++ software was really fun to use and made the job of creating this project so much easier. It serves as a really helpful support for those who want to pursue natural language processing, because there is so much that can be done with textual information. There is "no one size fits all" type of analyzer for text and NLP++ helps us realize the diversity but in the form of code.
No comments:
Post a Comment