Hi there
I am trying to build a resume shortlisting engine given a job description. Given that the job descriptions have information in form of sentences, it might yield a good embedding representation. However information within resumes is not much detailed, for e.g. skills delimited by comma mentioned within the Skills section. How can such limitation be addressed?
You can write some examples about the format of the output. In other words, the model can learn how to provide the output, based on your guidelines.
What have you tried? Do you have a corpus of resumes and job postings?
Hiya -
Technical Recruiter here… this has been an issue since keyword Boolean searches have been standard. Adding a human layer to validate or perhaps compelling the submitter to provide context might be a path to a useful tool.