用于对英语单词（名词，动词，副词等）进行语法分类的库

#1 楼

import java.io.BufferedReader;
import java.io.FileReader;
import java.util.List;

import edu.stanford.nlp.ling.Sentence;
import edu.stanford.nlp.ling.TaggedWord;
import edu.stanford.nlp.ling.HasWord;
import edu.stanford.nlp.tagger.maxent.MaxentTagger;

class TaggerDemo {

  private TaggerDemo() {}

  public static void main(String[] args) throws Exception {
    if (args.length != 2) {
      System.err.println("usage: java TaggerDemo modelFile fileToTag");
      return;
    }
    MaxentTagger tagger = new MaxentTagger(args[0]);
    List<List<HasWord>> sentences = MaxentTagger.tokenizeText(new BufferedReader(new FileReader(args[1])));
    for (List<HasWord> sentence : sentences) {
      List<TaggedWord> tSentence = tagger.tagSentence(sentence);
      System.out.println(Sentence.listToString(tSentence, false));
    }
  }

}

#2 楼

import nltk

with open(file) as f:
    for line in f:
        tmp = nltk.word_tokenize(line)
        print nltk.pos_tag(tmp)

#3 楼

InputStream modelIn = null;

try {
  modelIn = new FileInputStream("en-pos-maxent.bin");
  POSModel model = new POSModel(modelIn);
}
catch (IOException e) {
  // Model loading failed, handle the error
  e.printStackTrace();
}
finally {
  if (modelIn != null) {
    try {
      modelIn.close();
    }
    catch (IOException e) {
    }
  }
}      

POSTaggerME tagger = new POSTaggerME(model);
String sent[] = new String[]{"Most", "large", "cities", "in", "the", "US", "had",
                             "morning", "and", "afternoon", "newspapers", "."};         
String tags[] = tagger.tag(sent);
double probs[] = tagger.probs(); // confidence scores for each tag
Sequence topSequences[] = tagger.topKSequences(sent); // Some applications need to retrieve the n-best pos tag sequences and not only the best sequence

#4 楼

#5 楼

from textblob import TextBlob

text = '''
The titular threat of The Blob has always struck me as the ultimate movie
monster: an insatiably hungry, amoeba-like mass able to penetrate
virtually any safeguard, capable of--as a doomed doctor chillingly
describes it--"assimilating flesh on contact.
Snide comparisons to gelatin be damned, it's a concept with the most
devastating of potential consequences, not unlike the grey goo scenario
proposed by technological theorists fearful of
artificial intelligence run rampant.
'''

blob = TextBlob(text)
blob.tags           # [('The', 'DT'), ('titular', 'JJ'),
                    #  ('threat', 'NN'), ('of', 'IN'), ...]

blob.noun_phrases   # WordList(['titular threat', 'blob',
                    #            'ultimate movie monster',
                    #            'amoeba-like mass', ...])

for sentence in blob.sentences:
    print(sentence.sentiment.polarity)
# 0.060
# -0.341

blob.translate(to="es")  # 'La amenaza titular de The Blob...'

pip install -U textblob
python -m textblob.download_corpora

#6 楼

pip install spacy
python -m spacy.en.download

conda install spacy
python -m spacy.en.download

from spacy.parts_of_speech import ADV

def is_adverb(token):
    return token.pos == spacy.parts_of_speech.ADV

# These are data-specific, so no constants are provided. You have to look
# up the IDs from the StringStore.
NNS = nlp.vocab.strings['NNS']
NNPS = nlp.vocab.strings['NNPS']
def is_plural_noun(token):
    return token.tag == NNS or token.tag == NNPS

def print_coarse_pos(token):
    print(token.pos_)

def print_fine_pos(token):
    print(token.tag_)

#7 楼

import polyglot
from polyglot.text import Text, Word

text = Text(u"O primeiro uso de desobediência civil em massa ocorreu em setembro de 1906.")

print("{:<16}{}".format("Word", "POS Tag")+"\n"+"-"*30)
for word, tag in text.pos_tags:
    print(u"{:<16}{:>2}".format(word, tag))
Word            POS Tag
------------------------------
O               DET
primeiro        ADJ
uso             NOUN
de              ADP
desobediência   NOUN
civil           ADJ
em              ADP
massa           NOUN
ocorreu         ADJ
em              ADP
setembro        NOUN
de              ADP
1906            NUM
.               PUNCT