On Thu, Jun 19, 2014 at 3:44 AM, Juan Carlos Kuri Pinto via AGI < [email protected]> wrote:
> I would not use any mathematical tool unless it perfectly fits the problem > to solve. I doubt tensor products can solve NLP. But I can be wrong. I > would rather use analogical correspondences via Markov models for NLP. But > I can be wrong too. :) > If you model things as Markov chains of probabilities then you're really doing NLP and purely *syntactically*. But I think a more effective approach is to ignore the whims and irregularities of natural language and model "pure semantics" instead. That is the essence of a logic engine. We just need to find out the algebraic form of the semantics. The vectors / tensors can be seen as representations of the algebraic structure. ------------------------------------------- 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
