• View
• Edit
• History
• Print

Grammar

Stanford parser

• http://nlp.stanford.edu:8080/parser/ Stanford parser
  • See also http://nlp.stanford.edu/software/lex-parser.shtml
• Parts of speech tagging guidelines used for the Stanford parser http://www.ldc.upenn.edu/Catalog/desc/addenda/LDC1999T42/TAGGUID1.PDF
  • See also http://www.ldc.upenn.edu/Catalog/desc/addenda/LDC1999T42/ and http://www.cis.upenn.edu/~treebank/

I uploaded the Stanford parser to my hosted server and it works fine. I want to figure out how to make it accessible on the web as they have done at http://nlp.stanford.edu:8080/parser/. I can't peek under the hood of their page because it's down at the moment, but I assume it's just a matter of embedding the java in an html file, something I haven't done in long time. What I'd really like to do is get the Grammar browser to work online (see below).

There's an extension for this parser that outputs a tree-structure parse. It's located at:

• http://grammarbrowser.sourceforge.net/
  • Has moved to http://grammarscope.sourceforge.net/ 160803

I've installed this extension and it works beautifully, though only in English and French 'out of the box'. There must be a way to add the Chinese functionality of the Stanford parser to it. On that note, there must be a way to add traditional Chinese functionality to the Stanford parser without too much trouble. The grammar is no different; it's just a matter of using two different sets of fonts. They're already using CDICT... so I'm not sure why it's only built for simplified.

Phrase structure rules and constituents

• http://faculty.washington.edu/wassink/LING200/lect14_syntax2.pdf
  • See http://faculty.washington.edu/wassink/LING200 for index listing
• See the Wikipedia page http://en.wikipedia.org/wiki/Part_of_speech for discussion of lexical category

Odds and ends

Things I haven't had time to really look into yet.

• http://gate.ac.uk/sale/tao/splitch9.html#x11-2420009.13
  • http://gate.ac.uk/sale/tao/
• http://alg.ncsa.uiuc.edu/do/tools/t2k
  • This looks interesting and a free academic license is available: http://alg.ncsa.uiuc.edu/do/downloads/t2k.