I’m currently working on a project that screening skill in resumes and match it to the job description. My problem here is lack of data about each field in IT (such as web development, cloud computing,…), since I am building graph and hierarchical tree about it. I’ve been using NER from libraries to extract skills; however, I aim to find more standardized and extensive datasets. With sufficient data, skills can be categorized more accurately, enabling a more precise evaluation of candidates’ resumes.
My question is, besides using Wiki as a source, where else can I search for datasets containing keywords or ontologies specific to various IT domains? Thanks, everyone. p/s: Moreover, could anyone provide suggestions or guidance on constructing a hierarchical tree or graph for these relevant keywords?