I am currently testing & trying to improve some semantic search methods. The deeper I go into this field, the more I realize that the type of information retrieved -more precisely the niche the information belongs to (health, legal, history, etc.- influences the type of semantic search to use to retrieve accurate & relevant information.
I am already aware of some solutions such as wikipedia Dumps that provide a large xml files to parse. I also noted DBpedia and Wikiextractor. Furthermore, I also stumbled upon searchable index for wich some built-in functions exist like arXiv.
I’d like to know if there is a site that summarizes all database / solutions similar to the one I mentioned and if there are some related to specific niches? (the goal is obviously to avoid getting into web scrapping & directly plug into a specific datasource). I lack experience in this area, so if anyone found something useful I’ll be more than happy to get some advice.
Thank you very much