Stanford Natural Language Parser

The Stanford Natural Language Parser is installed on the Linguistics cluster. This is a probabilistic PCFG and dependency parser. To see a demo run the following command line:

/NLP_TOOLS/parsers/stanford_parser/latest/lexparser.csh /NLP_TOOLS/parsers/stanford_parser/latest/testsent.txt

For more details, see the Stanford Parser website.

The cluster also has a Ruby wrapper for this parser. Sample usage in the Ruby interactive mode:

$ irb
irb(main):001:0> require "stanfordparser"
=> true
irb(main):002:0> parser = StanfordParser::LexicalizedParser.new
Loading parser from serialized file /NLP_TOOLS/parsers/stanford_parser/latest/englishPCFG.ser.gz ... done [2.7 sec].
=> <edu.stanford.nlp.parser.lexparser.LexicalizedParser>
irb(main):003:0> puts parser.apply("This is a sentence.")
(ROOT
  (S [24.917]
    (NP [6.139] (DT [2.300] This))
    (VP [17.636] (VBZ [0.144] is)
      (NP [12.299] (DT [1.419] a) (NN [8.897] sentence)))
    (. [0.002] .)))

Sample usage with an example script:

$ ruby /opt/ruby-gems/lib/ruby/gems/1.8/gems/stanfordparser-1.1.0/examples/stanford-sentence-parser.rb "This is a sentence."
Loading parser from serialized file /NLP_TOOLS/parsers/stanford_parser/latest/englishPCFG.ser.gz ... done [3.1 sec].
(ROOT
  (S [24.917]
    (NP [6.139] (DT [2.300] This))
    (VP [17.636] (VBZ [0.144] is)
      (NP [12.299] (DT [1.419] a) (NN [8.897] sentence)))
    (. [0.002] .)))

-- BillMcNeill - 05 Nov 2007