Module: ArkTweetNlp::Parser
- Defined in:
- lib/ark_tweet_nlp/parser.rb
Constant Summary collapse
- TAGSET =
{ :N => 'common noun', :O => 'pronoun, non possessive', :^ => 'proper noun', :S => 'nominal + possessive', :Z => 'proper noun + possessive', :V => 'verb including copula, auxiliaries', :L => 'nominal + verbal (e.g. i’m), verbal + nominal (let’s)', :M => 'proper noun + verbal', :A => 'adjective', :R => 'adverb', :! => 'interjection', :D => 'determiner', :P => 'pre- or postposition, or subordinating conjunction', :& => 'coordinating conjunction', :T => 'verb particle', :X => 'existential there, predeterminers', :Y => 'X + verbal', :'#' => 'hashtag (indicates topic/category for tweet)', :'@' => 'at-mention (indicates a user as a recipient of a tweet)', :~ => 'discourse marker, indications of continuation across multiple tweets', :U => 'URL or email address', :E => 'emoticon', :'$' => 'numeral', :',' => 'punctuation', :G => 'other abbreviations, foreign words, possessive endings, symbols, garbage' }
- TAGGER_PATH =
spec = Gem::Specification.find_by_name(“ark_tweet_nlp”) gem_root = spec.gem_dir gem_bin = gem_root + “/bin”
File.join(Gem::Specification.find_by_name("ark_tweet_nlp").gem_dir, 'bin', 'runTagger.sh')
Class Method Summary collapse
Class Method Details
.find_tags(text) ⇒ Object
41 42 43 44 |
# File 'lib/ark_tweet_nlp/parser.rb', line 41 def Parser. text result = Parser.run_tagger(text) result.split("\n").map{ |line| Parser.convert_line( line ) } end |
.get_words_tagged_as(tagged_result, *tags) ⇒ Object
46 47 48 |
# File 'lib/ark_tweet_nlp/parser.rb', line 46 def Parser.get_words_tagged_as tagged_result, * Parser.merge_array( tagged_result.map{ |e| Parser.safe_invert( e ).select{ |key| .include? key } }) end |
.ola ⇒ Object
37 38 39 |
# File 'lib/ark_tweet_nlp/parser.rb', line 37 def Parser.ola "ola" end |