Author Archives: Linas Vepstas

About Linas Vepstas

Computer Science Researcher

Meaning-Text Theory

During some recent reading, it struck me that a useful framework for thinking about and talking about sentence generation is the MTT or “meaning-text theory” of Igor Mel’cuk, et al Here is one readable reference:

Igor A. Mel’čuk and …

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

Semantic dependency relations

I spent the weekend comparing the Stanford parser to RelEx, and learned a lot. RelEx really does deserve to be called a “semantic relation extractor”, and not just a “dependency relation extractor”. It provides a more abstract, …

Posted in Design, Development, Documentation, Theory | Tagged , , , , , , , | Leave a comment

Sentence Patterns

I’ve recently resumed work on the question-answering chatbot, and am trying to get it to comprehend a broader range of questions and statements.   The “big idea” is to create a number of “sentence patterns” that the pattern matcher can …

Posted in Design, Introduction, Theory | Tagged , , , , , | 2 Comments

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 links to its right or left: for …

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

proto-chatbot at last!

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

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

Posted in Development, Theory | Tagged , , , , , , | 3 Comments

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

Posted in Design, Theory | Tagged , , , , | 5 Comments

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 marginally better” “I am done working” “I asked …

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

scheme shell

I needed the ability to hand-edit opencog data while other processes were running. And so I hacked with guile for a while, and now there’s a scheme shell for opencog.
So far it’s very simple: just say ‘scm’ at the …

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

Software code quality

I spent the weekend creating a small, simple shim to import WordNet data into OpenCog. it got me to thinking about software quality. At first, I intended to use the NLTK Python interfaces into the wordnet data … it …

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