def stanford_tag(sentence): ''' use stanford tagger to tag a single tokenized sentence ''' import src.experiment.path as path tagger = POSTagger(path.stanford_tagger_model_path(), path.stanford_tagger_path(), java_options='-Xmx16g -XX:MaxPermSize=256m') return tagger.tag(sentence)
def stanford_batch_tag(sentences): '''use stanford tagger to batch tag a list of tokenized sentences ''' import src.experiment.path as path # need to replace the model path and tagger path of standford parser # in your computer (I use two functions here, you can hard code the paths if # you like) tagger = POSTagger(path.stanford_tagger_model_path(), path.stanford_tagger_path()) return tagger.batch_tag(sentences)