sunshineclt / n-gram
Sina News Crawler and Word Segmentation
☆13Updated 7 years ago
Alternatives and similar repositories for n-gram:
Users that are interested in n-gram are comparing it to the libraries listed below
- 基于情感词典的热门话题 的情感分析☆8Updated 10 years ago
- ☆10Updated 8 years ago
- A Chinese Words Segmentation Tool Based on Bayes Model☆80Updated 11 years ago
- tag doc using topN words with lda☆10Updated 9 years ago
- a bilstm-seq2seq ner script from baidu-ner contest☆9Updated 8 years ago
- 深度学习相关资料☆13Updated 9 years ago
- 通过分析客户和客服对话,对客户的问题进行一些分类。☆9Updated 7 years ago
- Facebook faiss相关的python接口☆15Updated 5 years ago
- A tool to get the arxiv papers☆19Updated 7 years ago
- framework for data mining, and c++ language used.☆23Updated 11 years ago
- 《知网》中文词语语义相似度算法☆41Updated 11 years ago
- A GBDT(MART) and LambdaMART training and predicting package☆14Updated 9 years ago
- chinese word segmentation based on rnn☆12Updated 8 years ago
- 信息检索检索器的Java实现☆16Updated 7 years ago
- 基于标题分类的主题句提取方法可描述为: 给定一篇新闻报道, 计算标题与新闻主题词集的相似度, 判断标题是否具有提示性。对于提示性标题,抽取新闻报道中与其最相似的句子作为主题句; 否则, 综合利用多种特征计算新闻报道中句子的重要性, 将得分最高的句子作为主题句。☆40Updated 8 years ago
- Using RNN for Chinese fixed-head poem(藏头诗) creation.☆15Updated 9 years ago
- solution for the 5th place of cikm cup 2014☆19Updated 10 years ago
- 代码讲解部分请前往blog:http://lan2720.github.io/☆34Updated 8 years ago
- A high level API based on Tensorflow☆30Updated 8 years ago
- use CNN to solve problem of Chinese Sentence classification☆9Updated 8 years ago
- 为给定的一段文本抽取一个或多个基于知识树的标签。☆8Updated 9 years ago
- CRFs based Chinese word segmentor☆19Updated 10 years ago
- 中文维基百科问答语料采集系统☆11Updated 7 years ago
- 基于TMSVM的微博情感正负判断☆16Updated 10 years ago
- Chinese Word Segmention Base on the Deep Learning and LSTM Neural Network☆21Updated 8 years ago
- Generate Chinese poem automatically.☆19Updated 9 years ago
- 实现中文文本分类,支持文件、文本分类,基于多项式分布的朴素贝叶斯分类器。由于工作实际应用是二分类,加之考虑到每个分类属性都建立map存储词语向量可能引起的内存问题,所以目前只支持二分类。当然,直接复用这个结构扩展到多分类也是很容易。之所以自己写,主要原因是没有仔细研读mah…☆22Updated 8 years ago
- Quora Duplicated Question Challenge (Kaggle Competition)☆10Updated 7 years ago
- 这是一个使用中科院计算所分词器的历史答题系统, 能够建立简单的知识图谱, 并通过计算关联项决定答案。☆13Updated 9 years ago
- Chinese word segmentation algorithm based on entropy(基于熵,无需语料库的中文分词)☆11Updated 7 years ago