stanford-core-nlp example

example.rb

require 'stanford-core-nlp'

root = Dir.pwd

# Set an alternative path to look for the JAR files
# Default is gem's bin folder.
StanfordCoreNLP.jar_path = root + '/stanford-core-nlp-full/'

# Set an alternative path to look for the model files
# Default is gem's bin folder.
StanfordCoreNLP.model_path = root + '/stanford-core-nlp-full/'

# Pass some alternative arguments to the Java VM.
# Default is ['-Xms512M', '-Xmx1024M'] (be prepared
# to take a coffee break).
#StanfordCoreNLP.jvm_args = ['-option1', '-option2']

# Redirect VM output to log.txt
StanfordCoreNLP.log_file = 'log.txt'

# Change a specific model file.
StanfordCoreNLP.set_model('pos.model', 'english-left3words-distsim.tagger')

# Use the model files for a different language than English.
StanfordCoreNLP.use :french # or :german

text = 'Angela Merkel met Nicolas Sarkozy on January 25th in ' +
   'Berlin to discuss a new austerity package. Sarkozy ' +
   'looked pleased, but Merkel was dismayed.'

pipeline =  StanfordCoreNLP.load(:tokenize, :ssplit, :pos, :lemma, :parse, :ner, :dcoref)
text = StanfordCoreNLP::Annotation.new(text)
pipeline.annotate(text)

text.get(:sentences).each do |sentence|
  # Syntatical dependencies
  puts sentence.get(:basic_dependencies).to_s
  sentence.get(:tokens).each do |token|
    # Default annotations for all tokens
    puts token.get(:value).to_s
    puts token.get(:original_text).to_s
    puts token.get(:character_offset_begin).to_s
    puts token.get(:character_offset_end).to_s
    # POS returned by the tagger
    puts token.get(:part_of_speech).to_s
    # Lemma (base form of the token)
    puts token.get(:lemma).to_s
    # Named entity tag
    puts token.get(:named_entity_tag).to_s
    # Coreference
    puts token.get(:coref_cluster_id).to_s
    # Also of interest: coref, coref_chain, 
    # coref_cluster, coref_dest, coref_graph.
  end
end