I need to merge two ontologies together to a single file based on semantic similarity of concepts. For doing this, I use nlp for determining similar concepts semantically. There are cases that ontology concepts are named in camelcase or underscores to separated way. Are there any algorithms to semantically match camelcase or underscore separated words? What I need is semantically match two concepts which are named in camelcase of underscore separated way. This image has an ontology that contain concepts with camelcase namings. If there are no algorithms, please could you suggest a way?
I already found some algorithms for matching two words or sentences semantically (SEMILAR Library, cortical.io, Similarity Library and of course, WordNet). But none of them can match two camelcase or underscore separated words semantically. I know we can try by separating the words of the camelcase. But I have no clue what to do next. I am also new to nlp and I don't know if there a simple way to achieve this.
I expect an algorithm or a way that matches two camelcase or underscore separated words semantically and outputting a similarity score to determine the semantic similarity of them.
Update:
I also found this WS4J demo for measuring semantic similarity between words and sentences. But still cannot use it for camelcase and underscore separated words.
