- Use chinease natual language processing library NLPIR-ICTCLAS to do the work like Chinease word segmentation and part-of-speech tagging.
- Preprocessing.
- Use word2vec gensim to train the model and caculate the similarity.
juanblak / chinease-keyword-similarity Goto Github PK
View Code? Open in Web Editor NEWUse Chinese natural language processing library to preprocess the novels and then train the word2vec model and calculate the similarity.