/chatbot-zh-torch7

中文聊天机器人

Primary LanguageLua

Chatbot in chinese （中文聊天机器人）

Installing

  1. Install Torch.

  2. Install the following additional Lua libs:

    luarocks install nn
luarocks install rnn
luarocks install penlight

    To train with CUDA install the latest CUDA drivers, toolkit and run:

    luarocks install cutorch
luarocks install cunn

    To train with opencl install the lastest Opencl torch lib:

    luarocks install cltorch
luarocks install clnn

  3. Download the dgk_lost_conv 中文对白语料 and unzip results/xiaohuangji50w_fenciA.conv.zip into data/.

Training

th train.lua [-h / options]

Use the --dataset NUMBER option to control the size of the dataset. Training on the full dataset takes about 5h for a single epoch.

The model will be saved to data/model.t7 after each epoch if it has improved (error decreased).

Testing

To load the model and have a conversation:

th eval.lua

##How Use https://github.com/dgkae/dgk_lost_conv as training corpus. The chinese sentenses should be splited by semantic words, using '/'. We modify cornell_movie_dialog.lua to support it. Lua save all string(e.g. chinese) all in multibyte, so in chinese the formal pl.lexer is not working. We use outsider word-splitting tool and using '/' as the tag.

##Result

result result2

License

MIT