zhanzecheng / Chinese_segment_augmentLinks
python3实现互信息和左右熵的新词发现
☆592Updated 5 years ago
Alternatives and similar repositories for Chinese_segment_augment
Users that are interested in Chinese_segment_augment are comparing it to the libraries listed below
Sorting:
- 速度更快、效果更好的中文新词发现☆511Updated last year
- 中文文本语义相似度(Chinese Semantic Text Similarity)语料库建设☆480Updated 7 years ago
- 综合了同义词词林扩展版与知网(Hownet)的词语相似度计算方法,词汇覆盖更多、结果更准确。☆729Updated 3 years ago
- 自然语言基础模型☆563Updated 6 years ago
- 使用预训练语言模型BERT做中文NER☆956Updated 5 years ago
- self complement of Sentence Similarity compute based on cilin, hownet, simhash, wordvector,vsm models,基于同义词词林,知网,指纹,字词向量,向量空间模型的句子相似度计算。☆361Updated 6 years ago
- bert中文分类实践☆736Updated 6 years ago
- 问题句子相似度计算,即给定客服里用户描述的两句话,用算法来判断是否表示了相同的语义。☆370Updated 4 years ago
- Chinese Embedding collection incling token ,postag ,pinyin,dependency,word embedding.中文自然语言处理向量合集,包括字向量,拼音向量,词向量,词性向量,依存关系向量.共5种类型的向量☆455Updated 6 years ago
- 常用文本匹配模型tf版本,数据集为QA_corpus,持续更新中☆674Updated 5 years ago
- Time-NLP的python3版本 中文时间表达词转换☆517Updated 2 years ago
- An collection of Chinese nlp corpus including basic Chinese syntatic wordset, semantic wordset, historic corpus and evaluate corpus. 中文自然…☆448Updated 6 years ago
- 文本匹配的相关模型DSSM,ESIM,ABCNN,BIMPM等,数据集为LCQMC官方数据☆468Updated 3 years ago
- 基于哈工大同义词词林扩展版的单词相似度计算方法☆366Updated 2 years ago
- BERT模型从训练到部署☆527Updated 4 years ago
- 使用预训练语言模型ALBERT做中文NER☆475Updated 4 years ago
- 2019年百度的三元组抽取比赛,“科学空间队”源码☆768Updated 5 years ago
- Comparison of Chinese Named Entity Recognition Models between NeuroNER and BertNER☆332Updated 5 years ago
- SiameseSentenceSimilarity,个人实现的基于Siamese bilstm模型的相似句子判定模型,提供训练数据集和测试数据集.☆268Updated 5 years ago
- 简易的中文纠错和消歧☆289Updated 9 years ago
- ai challenger 2018细粒度情感 分类第一名解决方案, A training framework itegrating tensorflow and pytorch☆581Updated 2 years ago
- 今日头条中文新闻文本(多层)分类数据集☆395Updated 4 years ago
- 神策杯2018高校算法大师赛(中文关键词提取)第二名代码方案☆308Updated 5 years ago
- details☆263Updated 7 years ago
- 专注于可解释的NLP技术 An NLP Toolset With A Focus on Explainable Inference☆621Updated 4 years ago
- 对四种句子/文本相似度计算方法进行实验与比较☆289Updated 4 years ago
- Macadam是一个以Tensorflow(Keras)和bert4keras为基础,专注于文本分类、序列标注和关系抽取的自然语言处理工具包。支持RANDOM、WORD2VEC、FASTTEXT、BERT、ALBERT、ROBERTA、NEZHA、XLNET、ELECTRA…☆325Updated 2 years ago
- BDCI 2018 汽车行业用户观点主题及情感识别 决赛一等奖方案☆429Updated 6 years ago
- ☆268Updated 5 years ago
- 在Keras下微调Bert的一些例子;some examples of bert in keras☆655Updated 5 years ago