Generating skill data through machine learning

One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause performance of a method of generating skill data for job search, job hiring, or skill research, the method comprising:

• obtaining a graph for each skill name of a plurality of skill names;
• obtaining a hypernym tree for a word selected from each skill name of the plurality of skill names,
• the hypernym tree including a node for each meaning of one or more meanings of the word,
• at least one hypernym tree of the hypernym trees including nodes for meanings of different words;
• assigning, for each skill name of the plurality of skill names, a meaning of the word selected from the skill name to the skill name based on the hypernym tree for the word;
• connecting two graphs for two skill names when two nodes for two meanings assigned to the two skill names are no more than a first threshold distance apart in a hypernym tree, to obtain a knowledge graph;
• receiving a request related to a skill;
• identifying, in response to the request, a certain graph for a certain skill name and a subgraph of the knowledge graph comprising nodes within a second threshold distance from the certain graph;
• generating and transmitting a response to the request including skill names corresponding to nodes in the subgraph.