Rodas, Amen, Shujing, Linas, other humans... Here are some thoughts on an approach to (unsupervised) learning of semantic similarities between syntactically different expressions with similar meanings... using frequent subhypergraph mining and then some statistical calculations...
These ideas emerged out of a long discussion btw Ruiting and me today... http://wiki.opencog.org/w/Learning_Semantic_Similarities_Between_Syntactic_Constructs_via_Pattern_Mining_and_Statistical_Analysis This is a step in the direction of unsupervised language learning a la http://arxiv.org/abs/1401.3372 but also of shorter-term value in enabling smarter inference on information extracted from text using RelEx2Logic, http://wiki.opencog.org/w/RelEx2Logic_Rules -- Ben -- Ben Goertzel, PhD http://goertzel.org "In an insane world, the sane man must appear to be insane". -- Capt. James T. Kirk ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
