LinkGrammar-WN is a lexicon expansion for the Link Grammar Parser. The Link Grammar Parser is a syntactic parser of the English language that is capable of handling a wide variety of syntactic constructions and is considered quite robust.

The LinkGrammar-WN project aims to import lexical information from WordNet. WordNet is an online lexical reference system that in recent years has become a popular tool for AI researchers.
This is an ongoing project. The LinkGrammar-WN v1.0 release contains 14,392 noun word forms not available within the original LGP lexicon, thus increasing the size of the LGP lexicon by 25%.

Author
  • LinkGrammar-WN was written by Elliot Turner (ell_NOSPAM_iot@eturner.net).
back to top
References:
  • The LinkGrammar-WordNet project is based on and inspired by the paper: "Adding a Medical Lexicon to an English Parser", by Szolovits, P. -- Project Page: http://www.cdm.lcs.mit.edu/projects/text/
  • LinkGrammar-WordNet uses lexical information extracted from the WordNet project. Thank you to the WordNet developers for making this resource available to the public.
back to top
News:
  • NEW! Oct 7, 2003 - LinkGrammar-WN v1.0 has been released! This version utilizes an automated word sense scoring algorithm to categorize WordNet nouns into the appropriate Link Grammar Parser dictionary word files. 14,392 noun word forms not available within the original LGP lexicon are now available.
back to top
Features:
  • Uses an automated word sense scoring algorithm to categorize WordNet words into the appropriate Link Grammar Parser dictionary files.
  • 14,392 noun word forms not found in the original LGP lexicon.
back to top
Downloads & Documentation:
back to top

Note: Link-Grammar-WN is distributed under the terms of the GNU General Public License. Dictionary data included within Link-Grammar-WN is distributed under a different license (specifically the WordNet license). Licensing information for this data is included with the Link-Grammar-WN distribution. The Link Grammar Parser falls under a separate license whose information can be viewed at the Link Grammar website.