daishengdong / WordSimilarity
基于知网的语义相似度计算
☆33Updated 10 years ago
Related projects ⓘ
Alternatives and complementary repositories for WordSimilarity
- 中文短文句相似读☆135Updated 6 years ago
- 新词发现☆68Updated 10 years ago
- 关系抽取实验☆33Updated 8 years ago
- mltk web edition☆40Updated 8 years ago
- code for NER using HMM;s and linear chain CRF's☆49Updated 8 years ago
- A Chinese word segment model based on BERT, F1-Score 97%☆90Updated 5 years ago
- A Java implementation of doc2vec in ICML'14☆30Updated 9 years ago
- a complete Java port of crfpp(crf++)☆31Updated 6 years ago
- ltp4j: Language Technology Platform For Java☆162Updated 3 years ago
- Details of paper cw2vec☆83Updated 6 years ago
- Chinese Tokenizer; New words Finder. 中文三段式机械分词算法; 未登录新词发现算法☆95Updated 8 years ago
- [Broken] A Chinese Question and Answer System☆51Updated 8 years ago
- A Joint Chinese segmentation and POS tagger based on bidirectional GRU-CRF☆151Updated 6 years ago
- A Java implementation of doc2vec in ICML'14☆25Updated 9 years ago
- Entity Linking，识别给 定文本中出现的命名实体（Named Entity），并映射到特定的知识库中唯一的实体。包括命名实体识别、消歧等工作。☆72Updated 5 years ago
- Train Wikidata with word2vec for word embedding tasks☆123Updated 6 years ago
- 新词发现算法(NewWordDetection)☆93Updated 3 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。☆39Updated 8 years ago
- Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"☆136Updated 3 years ago
- 基于句法分析的命名实体关系抽取程序☆65Updated 8 years ago
- 基于深度学习的自然语言处理库☆152Updated 6 years ago
- 基于知识库信息的词向量模型☆50Updated 5 years ago
- Chinese Open Information Extraction (Tree-based Triple Relation Extraction Module)☆119Updated 7 years ago
- Chinese new word discovery☆42Updated 2 months ago
- NLPCC2017示例代码以及数据描述☆116Updated 7 years ago
- 语义相似度计算各种算法实现汇总☆45Updated 6 years ago
- 基于知识库的开放域问答系统的相关工作☆69Updated 6 years ago
- Code for NLPCC2016 Chinese Word Similarity Task☆18Updated 8 years ago