Posts Tagged ‘NLP’
Meaning-Text Theory
Posted by: linasv on: 2009-11-08
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 Alain Polguère, (1987) “A Formal Lexicon in Meaning-Text Theory”, Computational Linguistics, vol. 13, pp. 261-275.
portal.acm.org/citation.cfm?id=48160.48166
www.aclweb.org/anthology/J/J87/J87-3006.pdf
Within the [...]
Semantic dependency relations
Posted by: linasv on: 2009-10-05
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, more semantic output than the Stanford parser, which sticks very narrowly to the syntactic structure of [...]
Sentence Patterns
Posted by: linasv on: 2009-09-08
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 recognize and respond to. The reason this is a “big” idea is because I am trying [...]
Frequency of grammatical disjuncts
Posted by: linasv on: 2009-07-06
- In: Development| Theory
- 2 Comments
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, verbs have their subject on the left, and an object on the right. Link-grammar defines [...]
Distribution of Mutual Information
Posted by: linasv on: 2009-03-11
- In: Development| Theory
- 1 Comment
A bit of corpus linguistics is performed to examine the mutual information distribution of word pairs.
Determining word senses from grammatical usage
Posted by: linasv on: 2009-01-12
- In: Design| Theory
- 2 Comments
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 some heavy statistical NLP work, computing statistical correlations between word senses and syntax — specifically, [...]
Hacking on Link-Grammar
Posted by: linasv on: 2008-08-17
- In: Design| Development| Theory
- 3 Comments
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 a question” “I was told that crap, too” all parse correctly.
Solving these required adding new [...]
Mapping Wordnet, RelEx to OpenCog
Posted by: linasv on: 2008-05-05
- In: Design| Theory
- Leave a Comment
I spent the afternoon creating a formalized mapping from RelEx and Wordnet to OpenCog. The goal is to clean things up enough so that I can run word-sense disambiguation code with opencog itself. Now, one thing that was nagging me is that this is, in some sense, the hard-way forward — I could just [...]
Google Summer of Code
Posted by: dhart on: 2008-05-05
Crunch time is here! Our participation in Google’s Summer of Code program has accelerated release schedules and shifted priorities. Ben is busy writing initial documentation, converting much of it from Novamente documentation. Gustavo, Senna and Linas are working to tidy OpenCog code, removing crufty and embarrassing bits and improving infrastructure and interfaces. Joel is working [...]
- jasonforceau: Hi, i am looking for tools for syntactic analysis for the system of my Final Year Project and found your post so interesting. But I don't know Link-Gr
- linasv: These graphs were discussed on the corpora mailing list in March 2009. See http://mailman.uib.no/public/corpora/2009-March/008193.html and followups i
- linasv: Martin Reynaert wrote to say: ''From what I have learned from the work of mainly Ramon Ferrer i Cancho ( http://www.lsi.upc.edu/~rferrericancho/p
OpenCog on del.icio.us
- An error has occurred; the feed is probably down. Try again later.
