Tag Archives: NLP

Frequency of grammatical disjuncts

Posted on July 6, 2009 by Linas Vepstas

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 links to its right or left: for example, … Continue reading →

Posted in Development, Theory | Tagged , , , , , | 4 Comments

proto-chatbot at last!

Posted on April 28, 2009 by Linas Vepstas

A prototype chatbot demonstrates the OpenCog NLP pipeline by parsing simple statements and answering simple questions. Continue reading →

Posted in Development, Meta, Theory | Tagged , , , , | Leave a comment

Distribution of Mutual Information

Posted on March 11, 2009 by Linas Vepstas

A bit of corpus linguistics is performed to examine the mutual information distribution of word pairs. Continue reading →

Posted in Development, Theory | Tagged , , , , , , | 2 Comments

Determining word senses from grammatical usage

Posted on January 12, 2009 by Linas Vepstas

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 terrible), and lightning-fast.  I’m doing this by doing … Continue reading →

Posted in Design, Theory | Tagged , , , , | 7 Comments

Hacking on Link-Grammar

Posted on August 17, 2008 by Linas Vepstas

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 marginally better” “I am done working” “I asked Jim … Continue reading →

Posted in Design, Development, Theory | Tagged , , , , | 6 Comments