CRF,LSTM,最大后向匹配法实现中文分词

上传者: sixi5498 | 上传时间: 2019-12-21 21:07:39 | 文件大小: 14.89MB | 文件类型: rar
3种中文分词方法:最大后向匹配法,CRF,LSTM。其中LSTM又用了三种方法输入,glove向量,Word2vec向量,还有将字映射成整数再通过embedding层映射成字向量作为输入。还包含中文分词的评分脚本。

文件下载

资源详情

[{"title":"( 73 个子文件 14.89MB ) CRF,LSTM,最大后向匹配法实现中文分词","children":[{"title":"中文分词","children":[{"title":"CRF++","children":[{"title":"make_crf_train_data.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"crf_data_2_word.py <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"libcrfpp.dll <span style='color:#111;'> 329.50KB </span>","children":null,"spread":false},{"title":"crf_test.exe <span style='color:#111;'> 49.50KB </span>","children":null,"spread":false},{"title":"make_crf_test_data.py <span style='color:#111;'> 890B </span>","children":null,"spread":false},{"title":"crf_learn.exe <span style='color:#111;'> 49.50KB </span>","children":null,"spread":false},{"title":"read me.docx <span style='color:#111;'> 67.96KB </span>","children":null,"spread":false},{"title":"template <span style='color:#111;'> 238B </span>","children":null,"spread":false}],"spread":true},{"title":"word2vec向量作为lstm中文分词输入","children":[{"title":"msr_train.txt <span style='color:#111;'> 23.26MB </span>","children":null,"spread":false},{"title":"pre_data.py <span style='color:#111;'> 1.62KB </span>","children":null,"spread":false},{"title":"word2vec_test.py <span style='color:#111;'> 4.11KB </span>","children":null,"spread":false},{"title":"bi_lstm_model.py <span style='color:#111;'> 569B </span>","children":null,"spread":false},{"title":"word2vec_train.py <span style='color:#111;'> 3.01KB </span>","children":null,"spread":false},{"title":"read me.docx <span style='color:#111;'> 11.59KB </span>","children":null,"spread":false}],"spread":true},{"title":"score <span style='color:#111;'> 7.06KB </span>","children":null,"spread":false},{"title":"lstm","children":[{"title":"msr_train.txt <span style='color:#111;'> 23.26MB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 3.42KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 2.22KB </span>","children":null,"spread":false},{"title":"lstm_model.py <span style='color:#111;'> 817B </span>","children":null,"spread":false}],"spread":true},{"title":"最大后向匹配","children":[{"title":"common.py <span style='color:#111;'> 283B </span>","children":null,"spread":false},{"title":"bwd_max_match.py <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false}],"spread":true},{"title":"分词结果评分.docx <span style='color:#111;'> 32.99KB </span>","children":null,"spread":false},{"title":"glove向量作为lstm中文分词输入","children":[{"title":"GloVe-1.2","children":[{"title":"eval","children":[{"title":"octave","children":[{"title":"evaluate_vectors_octave.m <span style='color:#111;'> 3.37KB </span>","children":null,"spread":false},{"title":"WordLookup_octave.m <span style='color:#111;'> 214B </span>","children":null,"spread":false},{"title":"read_and_evaluate_octave.m <span style='color:#111;'> 833B </span>","children":null,"spread":false}],"spread":true},{"title":"python","children":[{"title":"evaluate.py <span style='color:#111;'> 4.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"matlab","children":[{"title":"read_and_evaluate.m <span style='color:#111;'> 812B </span>","children":null,"spread":false},{"title":"WordLookup.m <span style='color:#111;'> 204B </span>","children":null,"spread":false},{"title":"evaluate_vectors.m <span style='color:#111;'> 3.34KB </span>","children":null,"spread":false}],"spread":true},{"title":"question-data","children":[{"title":"gram8-plural.txt <span style='color:#111;'> 33.61KB </span>","children":null,"spread":false},{"title":"._gram6-nationality-adjective.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"gram1-adjective-to-adverb.txt <span style='color:#111;'> 34.03KB </span>","children":null,"spread":false},{"title":"gram6-nationality-adjective.txt <span style='color:#111;'> 50.96KB </span>","children":null,"spread":false},{"title":"gram5-present-participle.txt <span style='color:#111;'> 31.31KB </span>","children":null,"spread":false},{"title":"._gram3-comparative.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"capital-world.txt <span style='color:#111;'> 138.79KB </span>","children":null,"spread":false},{"title":"gram2-opposite.txt <span style='color:#111;'> 32.59KB </span>","children":null,"spread":false},{"title":"capital-common-countries.txt <span style='color:#111;'> 14.35KB </span>","children":null,"spread":false},{"title":"family.txt <span style='color:#111;'> 14.74KB </span>","children":null,"spread":false},{"title":"currency.txt <span style='color:#111;'> 22.38KB </span>","children":null,"spread":false},{"title":"._gram9-plural-verbs.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._gram2-opposite.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"gram9-plural-verbs.txt <span style='color:#111;'> 23.62KB </span>","children":null,"spread":false},{"title":"._capital-common-countries.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._gram4-superlative.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._gram8-plural.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._gram1-adjective-to-adverb.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"city-in-state.txt <span style='color:#111;'> 83.68KB </span>","children":null,"spread":false},{"title":"._city-in-state.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._gram5-present-participle.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"gram7-past-tense.txt <span style='color:#111;'> 46.54KB </span>","children":null,"spread":false},{"title":"._currency.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"gram4-superlative.txt <span style='color:#111;'> 30.16KB </span>","children":null,"spread":false},{"title":"._gram7-past-tense.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"gram3-comparative.txt <span style='color:#111;'> 32.77KB </span>","children":null,"spread":false},{"title":"._family.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false},{"title":"._capital-world.txt <span style='color:#111;'> 212B </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"demo.sh <span style='color:#111;'> 1.66KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 11.13KB </span>","children":null,"spread":false},{"title":"src","children":[{"title":"vocab_count.c <span style='color:#111;'> 7.26KB </span>","children":null,"spread":false},{"title":"glove.c <span style='color:#111;'> 16.58KB </span>","children":null,"spread":false},{"title":"shuffle.c <span style='color:#111;'> 7.63KB </span>","children":null,"spread":false},{"title":"cooccur.c <span style='color:#111;'> 18.64KB </span>","children":null,"spread":false}],"spread":true},{"title":"README <span style='color:#111;'> 1.95KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 262B </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 664B </span>","children":null,"spread":false}],"spread":true},{"title":"msr_train.txt <span style='color:#111;'> 23.26MB </span>","children":null,"spread":false},{"title":"pre_data.py <span style='color:#111;'> 1.10KB </span>","children":null,"spread":false},{"title":"glove_test.py <span style='color:#111;'> 4.33KB </span>","children":null,"spread":false},{"title":"glove_train.py <span style='color:#111;'> 3.15KB </span>","children":null,"spread":false},{"title":"bi_lstm_model.py <span style='color:#111;'> 569B </span>","children":null,"spread":false},{"title":"获取glove向量运行命令.txt <span style='color:#111;'> 474B </span>","children":null,"spread":false},{"title":"read me.docx <span style='color:#111;'> 46.98KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明