以spacy中函数调用为例记录对自然语言基本处理任务

# coding=utf-8

import spacy
nlp=spacy.load(‘en_core_web_md-1.2.1‘)
docx=nlp(u‘The ways to process documents are so varied and application- and language-dependent that I decided to not constrain them by any interface. Instead, a document is represented by the features extracted from it, not by its "surface" string form: how you get to the features is up to you. Below I describe one common, general-purpose approach (called bag-of-words), but keep in mind that different application domains call for different features, and, as always, it’s garbage in, garbage out...‘)

‘‘‘
功能测试
‘‘‘
#1.分词 tokenize
print ‘#################tokenization‘
for token in docx:
        print token
#2.词性标注 pos tagging
print ‘#################part of speech tagging‘
for token in docx:
        print(token, token.pos_, token.pos)
#3.命名实体识别 Named Entity Recognition
print ‘################# Named Entity Recognition‘
for ent in docx.ents:
        print(ent,ent.label_,ent.label)
#4.词干化 Lemmatize
print ‘#################Lemmatize‘
for token in docx:
        print(token,token.lemma_,token.lemma)        
#5.名词短语提取 Noun Phrase Extraction
print ‘#################Noun Phrase Extraction‘
for np in docx.noun_chunks:
        print np
#6.断句 Sentence segmentation
print ‘#################Sentence segmentation‘
for sent in docx.sents:
        print sent