Clik here to view.
Hacking on Link-Grammar
I hack, heads-down, on link-grammar every now and then. Yesterday, I fixed another round of broken parse rules: making sure that sentences like “John is altogether amazingly quick.” “That one is...
View ArticleClik here to view.
Determining word senses from grammatical usage
I’ve recently been tinkering with a mechanism for determining word senses based on their grammatical usage. This has me pretty excited, because, so far, it seems to be reasonably accurate (i.e. not...
View ArticleClik here to view.
proto-chatbot at last!
Hands-on tutorials are planned for the next month or so; we’ve already had a few on PLN, and my turn is coming up, for the opencog NLP pipeline. So I thought I’d wire up a cute demo for the occasion: a...
View ArticleClik here to view.
Frequency of grammatical disjuncts
The link-grammar parser uses labeled links to connect together pairs of words. In order to capture the idea of proper grammatical construction, any given word is only allowed to have very specific...
View ArticleSymbolic and Neural Nets: Two Sides of the Same Coin
Deep learning and neural nets are all the rage, today, and have displaced symbolic AI systems in most applications. It’s commonly believed that the two approaches have nothing to do with each other;...
View ArticleThe Viterbi Parser
I’ve recently made some good progress on something that I’m calling “the Viterbi decoder”, a new parser for the Link Grammar natural language parser. So I guess that means its time to talk a bit about...
View ArticleWhy Hypergraphs?
OpenCog uses hypergraphs to represent knowledge. Why? I don’t think this is clearly, succinctly explained anywhere, so I will try to do so here. This is a very important point: I can’t begin to tell...
View Article
