哈工大LTP进阶使用-三元组事件抽取
作者:互联网
哈工大LTP基本使用-分词、词性标注、依存句法分析、命名实体识别、角色标注
上一节我们讲了LTP的基本使用,接下来我们使用其进行事件抽取。
参考代码:https://github.com/liuhuanyong/EventTriplesExtraction
sentence_parser.py
import os
from pyltp import Segmentor, Postagger, Parser, NamedEntityRecognizer, SementicRoleLabeller
class LtpParser:
def __init__(self):
LTP_DIR = "../model/ltp_data_v3.4.0/"
self.segmentor = Segmentor()
self.segmentor.load_with_lexicon(os.path.join(LTP_DIR, "cws.model"),os.path.join(LTP_DIR, "user_dict.txt"))
self.postagger = Postagger()
self.postagger.load_with_lexicon(os.path.join(LTP_DIR, "pos.model"),os.path.join(LTP_DIR, "user_dict.txt"))
self.parser = Parser()
self.parser.load(os.path.join(LTP_DIR, "parser.model"))
self.recognizer = NamedEntityRecognizer()
self.recognizer.load(os.path.join(LTP_DIR, "ner.model"))
self.labeller = SementicRoleLabeller()
self.labeller.load(os.path.join(LTP_DIR, 'pisrl.model'))
'''语义角色标注'''
def format_labelrole(self, words, postags):
arcs = self.parser.parse(words, postags)
roles = self.labeller.label(words, postags, arcs)
roles_dict = {}
for role in roles:
roles_dict[role.index] = {arg.name:[arg.name,arg.range.start, arg.range.end] for arg in role.arguments}
return roles_dict
'''句法分析---为句子中的每个词语维护一个保存句法依存儿子节点的字典'''
def build_parse_child_dict(self, words, postags, arcs):
child_dict_list = []
format_parse_list = []
for index in range(len(words)):
child_dict = dict()
for arc_index in range(len(arcs)):
if arcs[arc_index].head == index+1: #arcs的索引从1开始
if arcs[arc_index].relation in child_dict:
child_dict[arcs[arc_index].relation].append(arc_index)
else:
child_dict[arcs[arc_index].relation] = []
child_dict[arcs[arc_index].relation].append(arc_index)
child_dict_list.append(child_dict)
rely_id = [arc.head for arc in arcs] # 提取依存父节点id
relation = [arc.relation for arc in arcs] # 提取依存关系
heads = ['Root' if id == 0 else words[id - 1] for id in rely_id] # 匹配依存父节点词语
for i in range(len(words)):
# ['ATT', '***', 0, 'nh', '总理', 1, 'n']
a = [relation[i], words[i], i, postags[i], heads[i], rely_id[i]-1, postags[rely_id[i]-1]]
format_parse_list.append(a)
return child_dict_list, format_parse_list
'''parser主函数'''
def parser_main(self, sentence):
words = list(self.segmentor.segment(sentence))
postags = list(self.postagger.postag(words))
arcs = self.parser.parse(words, postags)
child_dict_list, format_parse_list = self.build_parse_child_dict(words, postags, arcs)
roles_dict = self.format_labelrole(words, postags)
return words, postags, child_dict_list, roles_dict, format_parse_list
if __name__ == '__main__':
parse = LtpParser()
sentence = '中国是一个自由、和平的国家'
words, postags, child_dict_list, roles_dict, format_parse_list = parse.parser_main(sentence)
print(words, len(words))
print(postags, len(postags))
print(child_dict_list, len(child_dict_list))
print(roles_dict)
print(format_parse_list, len(format_parse_list))
结果:
['中国', '是', '一个', '自由', '、', '和平', '的', '国家'] 8
['ns', 'v', 'm', 'a', 'wp', 'a', 'u', 'n'] 8
[{}, {'SBV': [0], 'VOB': [7]}, {}, {'COO': [5], 'RAD': [6]}, {}, {'WP': [4]}, {}, {'ATT': [2, 3]}] 8
{1: {'A0': ['A0', 0, 0], 'A1': ['A1', 2, 7]}}
[['SBV', '中国', 0, 'ns', '是', 1, 'v'], ['HED', '是', 1, 'v', 'Root', -1, 'n'], ['ATT', '一个', 2, 'm', '国家', 7, 'n'], ['ATT', '自由', 3, 'a', '国家', 7, 'n'], ['WP', '、', 4, 'wp', '和平', 5, 'a'], ['COO', '和平', 5, 'a', '自由', 3, 'a'], ['RAD', '的', 6, 'u', '自由', 3, 'a'], ['VOB', '国家', 7, 'n', '是', 1, 'v']] 8
分别说一下每个结果的含义:
分词结果:
['中国', '是', '一个', '自由', '、', '和平', '的', '国家']
词性标注结果;
['ns', 'v', 'm', 'a', 'wp', 'a', 'u', 'n']
依存句法分析结果:
[{}, {'SBV': [0], 'VOB': [7]}, {}, {'COO': [5], 'RAD': [6]}, {}, {'WP': [4]}, {}, {'ATT': [2, 3]}]
注意,该数组的长度是8,对应着分词之后的每一个词。该结果是在原来的句法依存分析结果上进一步处理得到的,最初依存句法分析的结果是:
2:SBV 0:HED 8:ATT 8:ATT 6:WP 4:COO 4:RAD 2:VOB
同时,句法分析中的索引是从1开始的,也就是'中国'对应的是2:SBV,前面2是与中国具有关系的词的索引,SBV是具有的关系名,也就是【中国-是】是主谓关系。我们把每个词对应的关系维护成一个单独的字典。
角色标注结果:
{1: {'A0': ['A0', 0, 0], 'A1': ['A1', 2, 7]}}
整合结果:
[['SBV', '中国', 0, 'ns', '是', 1, 'v'], ['HED', '是', 1, 'v', 'Root', -1, 'n'], ['ATT', '一个', 2, 'm', '国家', 7, 'n'], ['ATT', '自由', 3, 'a', '国家', 7, 'n'], ['WP', '、', 4, 'wp', '和平', 5, 'a'], ['COO', '和平', 5, 'a', '自由', 3, 'a'], ['RAD', '的', 6, 'u', '自由', 3, 'a'], ['VOB', '国家', 7, 'n', '是', 1, 'v']]
这个就是将一个词的相关信息都放到一个列表里面,
triple_extraction.py
from sentence_parser import *
import re
import os
from time import time
from pprint import pprint
from pyltp import SentenceSplitter, Segmentor, Postagger, Parser
from utils import clean_text
from collections import Counter
class TripleExtractor:
def __init__(self):
self.parser = LtpParser()
'''文章分句处理, 切分长句,冒号,分号,感叹号等做切分标识'''
def split_sents(self, content):
return [sentence for sentence in re.split(r'[??!!。;;::\n\r]', content) if
sentence and '北京银行' in sentence and len(sentence) < 300]
'''利用语义角色标注,直接获取主谓宾三元组,基于A0,A1,A2'''
def ruler1(self, words, postags, roles_dict, role_index):
# words:['中国', '是', '一个', '自由', '、', '和平', '的', '国家']
# postags:['ns', 'v', 'm', 'a', 'wp', 'a', 'u', 'n']
# roles_dict:{1: {'A0': ['A0', 0, 0], 'A1': ['A1', 2, 7]}}
# role_index:1
v = words[role_index] # 是
role_info = roles_dict[role_index]
if 'A0' in role_info.keys() and 'A1' in role_info.keys():
s = ''.join([words[word_index] for word_index in range(role_info['A0'][1], role_info['A0'][2] + 1) if
postags[word_index][0] not in ['w', 'u', 'x'] and words[word_index]])
o = ''.join([words[word_index] for word_index in range(role_info['A1'][1], role_info['A1'][2] + 1) if
postags[word_index][0] not in ['w', 'u', 'x'] and words[word_index]])
if s and o:
return '1', [s, v, o]
# elif 'A0' in role_info:
# s = ''.join([words[word_index] for word_index in range(role_info['A0'][1], role_info['A0'][2] + 1) if
# postags[word_index][0] not in ['w', 'u', 'x']])
# if s:
# return '2', [s, v]
# elif 'A1' in role_info:
# o = ''.join([words[word_index] for word_index in range(role_info['A1'][1], role_info['A1'][2]+1) if
# postags[word_index][0] not in ['w', 'u', 'x']])
# return '3', [v, o]
return '4', []
'''三元组抽取主函数'''
def ruler2(self, words, postags, child_dict_list, roles_dict, arcs):
# words:['中国', '是', '一个', '自由', '、', '和平', '的', '国家']
# postags:['ns', 'v', 'm', 'a', 'wp', 'a', 'u', 'n']
# child_dict_list:[{}, {'SBV': [0], 'VOB': [7]}, {}, {'COO': [5], 'RAD': [6]}, {}, {'WP': [4]}, {}, {'ATT': [2, 3]}]
# roles_dict:{1: {'A0': ['A0', 0, 0], 'A1': ['A1', 2, 7]}}
# arcs:[['SBV', '中国', 0, 'ns', '是', 1, 'v'], ['HED', '是', 1, 'v', 'Root', -1, 'n'], ['ATT', '一个', 2, 'm', '国家', 7, 'n'], ['ATT', '自由', 3, 'a', '国家', 7, 'n'], ['WP', '、', 4, 'wp', '和平', 5, 'a'], ['COO', '和平', 5, 'a', '自由', 3, 'a'], ['RAD', '的', 6, 'u', '自由', 3, 'a'], ['VOB', '国家', 7, 'n', '是', 1, 'v']]
svos = []
for index in range(len(postags)): # [0,1,2,3,4,5,6,7]
tmp = 1
# 先借助语义角色标注的结果,进行三元组抽取
if index in roles_dict: # 1
flag, triple = self.ruler1(words, postags, roles_dict, index)
if flag == '1':
svos.append(triple)
tmp = 0
if tmp == 1:
# 如果语义角色标记为空,则使用依存句法进行抽取
# if postags[index] == 'v':
if postags[index]: # 是
# 抽取以谓词为中心的事实三元组
child_dict = child_dict_list[index]
# 主谓宾
# SBV:我送她一束花 (我 <– 送)
# VOB:我送她一束花 (送 –> 花)
if 'SBV' in child_dict and 'VOB' in child_dict:
r = words[index]
e1 = self.complete_e(words, postags, child_dict_list, child_dict['SBV'][0])
e2 = self.complete_e(words, postags, child_dict_list, child_dict['VOB'][0])
svos.append([e1, r, e2])
# 定语后置,动宾关系
# ATT:红苹果 (红 <– 苹果)
relation = arcs[index][0]
head = arcs[index][2]
if relation == 'ATT':
if 'VOB' in child_dict:
e1 = self.complete_e(words, postags, child_dict_list, head - 1)
r = words[index]
e2 = self.complete_e(words, postags, child_dict_list, child_dict['VOB'][0])
temp_string = r + e2
if temp_string == e1[:len(temp_string)]:
e1 = e1[len(temp_string):]
if temp_string not in e1:
svos.append([e1, r, e2])
# 含有介宾关系的主谓动补关系
# CMP:做完了作业 (做 –> 完)
# POB:在贸易区内 (在 –> 内)
if 'SBV' in child_dict and 'CMP' in child_dict:
e1 = self.complete_e(words, postags, child_dict_list, child_dict['SBV'][0])
cmp_index = child_dict['CMP'][0]
r = words[index] + words[cmp_index]
if 'POB' in child_dict_list[cmp_index]:
e2 = self.complete_e(words, postags, child_dict_list, child_dict_list[cmp_index]['POB'][0])
svos.append([e1, r, e2])
return svos
'''对找出的主语或者宾语进行扩展'''
def complete_e(self, words, postags, child_dict_list, word_index):
child_dict = child_dict_list[word_index]
prefix = ''
if 'ATT' in child_dict:
for i in range(len(child_dict['ATT'])):
prefix += self.complete_e(words, postags, child_dict_list, child_dict['ATT'][i])
postfix = ''
if postags[word_index] == 'v':
if 'VOB' in child_dict:
postfix += self.complete_e(words, postags, child_dict_list, child_dict['VOB'][0])
if 'SBV' in child_dict:
prefix = self.complete_e(words, postags, child_dict_list, child_dict['SBV'][0]) + prefix
return prefix + words[word_index] + postfix
'''程序主控函数'''
def triples_main(self, content):
# sentences = self.split_sents(content)
svos = []
sentence = content
# for sentence in sentences:
words, postags, child_dict_list, roles_dict, arcs = self.parser.parser_main(sentence)
svo = self.ruler2(words, postags, child_dict_list, roles_dict, arcs)
svos += svo
return svos
def test():
extractor = TripleExtractor()
contents = [
'中国是一个自由、和平的国家',
'他什么书都读',
'在贸易区内,他完成了交易',
'红色的苹果真好看',
'我送她一朵花',
'我做完了作业',
]
for content in contents:
print(extractor.triples_main(content))
test()
具体看注释。
结果:
[['中国', '是', '一个自由和平国家']]
[]
[['他', '完成', '交易']]
[]
[['我', '送', '一朵花']]
[['我', '做', '作业']]
标签:index,LTP,postags,self,三元组,哈工大,dict,words,child 来源: https://www.cnblogs.com/xiximayou/p/14701127.html