91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 40.13MB
    文件類型: .zip
    金幣: 1
    下載: 0 次
    發(fā)布日期: 2023-08-08
  • 語(yǔ)言: Python
  • 標(biāo)簽:

資源簡(jiǎn)介

一個(gè)非常簡(jiǎn)單的 BiLSTM-CRF 模型用于中文命名實(shí)體識(shí)別 (TensorFlow)

資源截圖

代碼片段和文件信息

import?sys?pickle?os?random
import?numpy?as?np

##?tags?BIO
tag2label?=?{“O“:?0
?????????????“B-PER“:?1?“I-PER“:?2
?????????????“B-LOC“:?3?“I-LOC“:?4
?????????????“B-ORG“:?5?“I-ORG“:?6
?????????????}


def?read_corpus(corpus_path):
????“““
????read?corpus?and?return?the?list?of?samples
????:param?corpus_path:
????:return:?data
????“““
????data?=?[]
????with?open(corpus_path?encoding=‘utf-8‘)?as?fr:
????????lines?=?fr.readlines()
????sent_?tag_?=?[]?[]
????for?line?in?lines:
????????if?line?!=?‘\n‘:
????????????[char?label]?=?line.strip().split()
????????????sent_.append(char)
????????????tag_.append(label)
????????else:
????????????data.append((sent_?tag_))
????????????sent_?tag_?=?[]?[]

????return?data


def?vocab_build(vocab_path?corpus_path?min_count):
????“““

????:param?vocab_path:
????:param?corpus_path:
????:param?min_count:
????:return:
????“““
????data?=?read_corpus(corpus_path)
????word2id?=?{}
????for?sent_?tag_?in?data:
????????for?word?in?sent_:
????????????if?word.isdigit():
????????????????word?=?‘
????????????elif?(‘\u0041‘?<=?word?<=‘\u005a‘)?or?(‘\u0061‘?<=?word?<=‘\u007a‘):
????????????????word?=?‘
????????????if?word?not?in?word2id:
????????????????word2id[word]?=?[len(word2id)+1?1]
????????????else:
????????????????word2id[word][1]?+=?1
????low_freq_words?=?[]
????for?word?[word_id?word_freq]?in?word2id.items():
????????if?word_freq?‘?and?word?!=?‘‘:
????????????low_freq_words.append(word)
????for?word?in?low_freq_words:
????????del?word2id[word]

????new_id?=?1
????for?word?in?word2id.keys():
????????word2id[word]?=?new_id
????????new_id?+=?1
????word2id[‘‘]?=?new_id
????word2id[‘‘]?=?0

????print(len(word2id))
????with?open(vocab_path?‘wb‘)?as?fw:
????????pickle.dump(word2id?fw)


def?sentence2id(sent?word2id):
????“““

????:param?sent:
????:param?word2id:
????:return:
????“““
????sentence_id?=?[]
????for?word?in?sent:
????????if?word.isdigit():
????????????word?=?‘
????????elif?(‘\u0041‘?<=?word?<=?‘\u005a‘)?or?(‘\u0061‘?<=?word?<=?‘\u007a‘):
????????????word?=?‘
????????if?word?not?in?word2id:
????????????word?=?‘
????????sentence_id.append(word2id[word])
????return?sentence_id


def?read_dictionary(vocab_path):
????“““

????:param?vocab_path:
????:return:
????“““
????vocab_path?=?os.path.join(vocab_path)
????with?open(vocab_path?‘rb‘)?as?fr:
????????word2id?=?pickle.load(fr)
????print(‘vocab_size:‘?len(word2id))
????return?word2id


def?random_embedding(vocab?embedding_dim):
????“““

????:param?vocab:
????:param?embedding_dim:
????:return:
????“““
????embedding_mat?=?np.random.uniform(-0.25?0.25?(len(vocab)?embedding_dim))
????embedding_mat?=?np.float32(embedding_mat)
????return?embedding_mat


def?pad_sequences(sequences?pad_mark=0):
????“““

????:param?sequences:
????:param?pad_mark:
????:return:
????“““
????max_len?=?max(map(lambda?x?:?len(x)?sequences))
????seq_list?seq_len_list?=?[]?[]
????for?seq?in?seque

?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\
?????文件??????????28??2019-03-16?13:58??zh-NER-TF-master\.gitignore
?????文件????????4103??2019-03-16?13:58??zh-NER-TF-master\README.md
?????文件???????12732??2019-03-16?13:58??zh-NER-TF-master\conlleval_rev.pl
?????文件????????3824??2019-03-16?13:58??zh-NER-TF-master\data.py
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\data_path\
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\data_path\original\
?????文件??????????49??2019-03-16?13:58??zh-NER-TF-master\data_path\original\link.txt
?????文件??????526458??2019-03-16?13:58??zh-NER-TF-master\data_path\original\test1.txt
?????文件??????577540??2019-03-16?13:58??zh-NER-TF-master\data_path\original\testright1.txt
?????文件????10480443??2019-03-16?13:58??zh-NER-TF-master\data_path\original\train1.txt
?????文件?????1114268??2019-03-16?13:58??zh-NER-TF-master\data_path\test_data
?????文件????13904440??2019-03-16?13:58??zh-NER-TF-master\data_path\train_data
?????文件???????61479??2019-03-16?13:58??zh-NER-TF-master\data_path\word2id.pkl
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\data_path_save\
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\checkpoints\
?????文件??????????79??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\checkpoints\checkpoint
?????文件????31417884??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\checkpoints\model-31680.data-00000-of-00001
?????文件????????1215??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\checkpoints\model-31680.index
?????文件?????5306570??2019-03-16?13:58??zh-NER-TF-master\data_path_save\1521112368\checkpoints\model-31680.meta
?????文件?????????778??2019-03-16?13:58??zh-NER-TF-master\eval.py
?????文件????????5605??2019-03-16?13:58??zh-NER-TF-master\main.py
?????文件???????12572??2019-03-16?13:58??zh-NER-TF-master\model.py
?????目錄???????????0??2019-03-16?13:58??zh-NER-TF-master\pics\
?????文件?????????961??2019-03-16?13:58??zh-NER-TF-master\pics\demo.txt
?????文件??????786270??2019-03-16?13:58??zh-NER-TF-master\pics\pic1.png
?????文件??????291153??2019-03-16?13:58??zh-NER-TF-master\pics\pic2.png
?????文件????????2814??2019-03-16?13:58??zh-NER-TF-master\utils.py

評(píng)論

共有 條評(píng)論

相關(guān)資源