我是NLP和IR程序的新手。我正在尝试实现深度NLP管道,即在句子的索引中添加Lemmatizing,依赖性解析功能。以下是我的模式和搜索器。
my_analyzer = RegexTokenizer()| StopFilter()| LowercaseFilter() | StemFilter() | Lemmatizer()
pos_analyser = RegexTokenizer() | StopFilter()| LowercaseFilter() | PosTagger()
schema = Schema(id=ID(stored=True, unique=True), stem_text=TEXT(stored= True, analyzer=my_analyzer), pos_tag= pos_analyser)
for sentence in sent_tokenize_list1:
writer.add_document(stem_text = sentence, pos_tag = sentence)
for sentence in sent_tokenize_list2:
writer.add_document(stem_text = sentence, pos_tag = sentence)
writer.commit()
with ix.searcher() as searcher:
og = qparser.OrGroup.factory(0.9)
query_text = MultifieldParser(["stem_text","pos_tag"], schema = ix.schema, group= og).parse(
"who is controlling the threat of locusts?")
results = searcher.search(query_text, sortedby= scores, limit = 10 )
这是自定义分析仪。
class PosTagger(Filter):
def __eq__(self, other):
return (other
and self.__class__ is other.__class__
and self.__dict__ == other.__dict__)
def __ne__(self, other):
return not self == other
def __init__(self):
self.cache = {}
def __call__(self, tokens):
assert hasattr(tokens, "__iter__")
words = []
tokens1, tokens2 = itertools.tee(tokens)
for t in tokens1:
words.append(t.text)
tags = pos_tag(words)
i=0
for t in tokens2:
t.text = tags[i][0] + " "+ tags[i][1]
i += 1
yield t
我遇到以下错误。
whoosh.fields.fields.fieldconfigurationerror:compositeanalyzer(regextokenizer(expression = re.compile(' w (。?? w )*'), gaps = false),stopfilter(stops = frozenset({'for',','will','tbd','with'with', "one_answers",','if','it','by','is'is'is'','','','as'as'as'as'as'as'his "我们","或",从",","您","'','can,'be',','','','','',','',','', " to"," on"," a"," an"," your"," at"," in",'','',''''','','}),, min = 2,max = none,renumber = true),lowercasefilter(), Postagger(cache = {}))不是fieldType对象
我做错了吗?这是将NLP管道添加到搜索引擎的正确方法吗?
pos_tag
应直接分配给TEXT(stored= True, analyzer=pos_analyzer)
的字段CC_2。
因此,在schema
中,您应该有:
schema = Schema(id=ID(stored=True, unique=True), stem_text=TEXT(stored= True, analyzer=my_analyzer), post_tag=TEXT(stored= True, analyzer=pos_analyzer))