我试图通过NLTK提出基本的分块概念,但最终还是会出现意想不到的意图错误
#Chunking
import nltk
from nltk.corpus import state_union
import matplotlib
from nltk.tokenize import PunktSentenceTokenizer
train_text = state_union.raw("2005-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(sample_text)
def process_stat():
try:
for w in tokenized:
words = nltk.word_tokenize(w)
tags = nltk.pos_tag(words)
chunkGram = r"""Chunk: {<RB.?>*<VB.?>*<NNP><NN>?}"""
chunkParser = nltk.RegexpParser(chunkGram)
chunked = chunkParser.parse(tags)
print(chunked)
文件“
”,第26行 ^
SyntaxError:解析时出现意外的EOF