bojone / word-discovery
速度更快、效果更好的中文新词发现
☆510Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for word-discovery
- python3实现互信息和左右熵的新词发现☆585Updated 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。☆359Updated 5 years ago
- Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法（论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained La…☆420Updated 4 years ago
- 中文文本语义相似度（Chinese Semantic Text Similarity）语料库建设☆472Updated 6 years ago
- a bert for retrieval and generation☆847Updated 3 years ago
- An off-the-shelf tool for Chinese Keyphrase Extraction 一个快速从中文里抽取关键短语的工具，仅占35M内存 www.jionlp.com☆540Updated last year
- An collection of Chinese nlp corpus including basic Chinese syntatic wordset, semantic wordset, historic corpus and evaluate corpus. 中文自然…☆438Updated 5 years ago
- Comparison of Chinese Named Entity Recognition Models between NeuroNER and BertNER☆328Updated 5 years ago
- 使用预训练语言模型ALBERT做中文NER☆467Updated 3 years ago
- 中文问题句子相似度计算比赛及方案汇总☆294Updated 3 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…☆324Updated last year
- Open Language Pre-trained Model Zoo☆987Updated 3 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☆450Updated 5 years ago
- 以词为基本单位的中文BERT☆458Updated 3 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。☆721Updated 2 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☆467Updated 2 years ago
- Modify Chinese text, modified on LaserTagger Model. 文本复述，基于lasertagger做中文文本数据增强。☆318Updated 10 months ago
- 基于哈工大同义词词林扩展版的单词相似度计算方法☆355Updated last year
- implementation several deep text match (text similarly) models for keras . cdssm, arc-ii,match_pyramid, mvlstm ,esim, drcn ,bimpm, bert, …☆291Updated 4 years ago
- CCKS 2019 中文短文本实体链指比赛技术创新奖解决方案☆411Updated last year
- ccks baidu entity link 实体链接 第一名☆843Updated 11 months 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。☆369Updated 4 years ago
- A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)☆417Updated 2 years ago
- 高质量中文预训练模型集合：最先进大模型、最快小模型、相似度专门模型☆805Updated 4 years ago
- 中文近义词表 Chinese Synonyms☆246Updated 6 years ago
- 使用预训练语言模型BERT做中文NER☆930Updated 4 years ago
- 文本相似度计算／文本匹配☆300Updated 4 years ago
- BERT模型从训练到部署☆521Updated 4 years ago
- ☆438Updated 2 years ago