# and rules for unknown words. See pattern.text.Morphology and pattern.text.Context
# for further details. A tutorial on how to acquire data for the lexicon is here:
# http://www.clips.ua.ac.be/pages/using-wiktionary-to-build-an-italian-part-of-speech-tagger
lexicon = Lexicon(
path = os.path.join(MODULE, "xx-lexicon.txt"),
morphology = os.path.join(MODULE, "xx-morphology.txt"),
context = os.path.join(MODULE, "xx-context.txt"),
entities = os.path.join(MODULE, "xx-entities.txt"),
language = "xx"
)
# Create the parser with default tags for unknown words:
# (noun, proper noun, numeric).
lexicon.load()
parser = Parser(
lexicon = lexicon,
default = ("NN", "NNP", "CD"),
language = "xx"
)
# Create the sentiment lexicon,
# see pattern/text/xx/xx-sentiment.xml for further details.
# We also need to define the tag for modifiers,
# words that modify the score of the following word
# (e.g., *very* good, *not good, ...)
sentiment = Sentiment(
path = os.path.join(MODULE, "xx-sentiment.xml"),
synset = None,
