- First, using cut_clean_corpus_tool.py to get clean and splited sentences.
- Second, using idf_cal_tool.py to cal the idf value of every words.
- Third, using word2vec_py_train.py for getting the embedding words.
- Fourth, using dump_qa_pair_2_sqlited3.py for writing the qa pair into database. Creating table sentence exist in data directory.
- At last, playing chatbot.py for fun.
benja-wu/toychatbot
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|