概述
這個工作嘗試重現這個論文的結果 A Neural Conversational Model (aka the Google chatbot).
它使用了循環神經網絡（seq2seq 模型）來進行句子預測。它是用 python 和 TensorFlow 開發。
程序的加載主體部分是參考 Torch的 neuralconvo from macournoyer.
現在, DeepQA 支持一下對話語料:
- Cornell Movie Dialogs corpus (default). Already included when cloning the repository.
- OpenSubtitles (thanks to Eschnou). Much bigger corpus (but also noisier). To use it, follow those instructions and use the flag
--corpus opensubs. - Supreme Court Conversation Data (thanks to julien-c). Available using
--corpus scotus. See the instructions for installation. - Ubuntu Dialogue Corpus (thanks to julien-c). Available using
--corpus ubuntu. See the instructions for installation. - Your own data (thanks to julien-c) by using a simple custom conversation format (See here for more info).
To speedup the training, it's also possible to use pre-trained word embeddings (thanks to Eschnou). More info here.
安裝
這個程序需要一下依賴(easy to install using pip: pip3 install -r requirements.txt):
- python 3.5
- tensorflow (tested with v1.0)
- numpy
- CUDA (for using GPU)
- nltk (natural language toolkit for tokenized the sentences)
- tqdm (for the nice progression bars)
你可能需要下載附帶的數據讓 nltk 正常工作。
python3 -m nltk.downloader punkt
Cornell 數據集已經包括了。其他的數據集查看 readme 文件到他們所在的文件夾。 (在 data/).
網站接口需要一些附加的包：
- django (tested with 1.10)
- channels
- Redis (see here)
- asgi_redis (at least 1.0)
Docker 安裝也是支持的，更多詳細的教程參考 here.
運行
聊天機器人
訓練這個模型，直接運行 main.py 。一旦訓練完成，你可以測試結果用 main.py --test
(結果生成在 'save/model/samples_predictions.txt') 或者用 main.py --test interactive (更有趣).
Here are some flags which could be useful. For more help and options, use python main.py -h:
--modelTag <name>: allow to give a name to the current model to differentiate between them when testing/training.--keepAll: use this flag when training if when testing, you want to see the predictions at different steps (it can be interesting to see the program changes its name and age as the training progress). Warning: It can quickly take a lot of storage space if you don't increase the--saveEveryoption.--filterVocab 20or--vocabularySize 30000: Limit the vocabulary size to and optimize the performances and memory usage. Replace the words used less than 20 times by the<unknown>token and set a maximum vocabulary size.--verbose: when testing, will print the sentences as they are computed.--playDataset: show some dialogue samples from the dataset (can be use conjointly with--createDatasetif this is the only action you want to perform).
To visualize the computational graph and the cost with TensorBoard, just run tensorboard --logdir save/.
默認的這個網絡架構是一個標准的 encoder/decoder 有兩個 LSTM layers (隱藏層大小 256) ，然后 vocabulary 的 embedding size 是 32.這個網絡用 ADAM 訓練。最大的句子長度設置為 10個單詞，但是可以增加。
結果
當然，這個網絡並不會很擅長聊天：
Q: Hi
A: Hi.
Q: What is your name ?
A: Laura.
Q: What does that mean ?
A: I dunno.
Q: How old are you ?
A: thirty-five.
Q: Will Google hire me ?
A: No.
Q: Tell me the alphabet
A: Fuck you.
Q: That's not nice
A: Yeah.
這里有一些情況它並不能正確回答：
Q: Who is Laura ?
A: My brother.
Q: Say 'goodbye'
A: Alright.
Q: What is cooking ?
A: A channel.
Q: Can you say no ?
A: No.
Q: Two plus two
A: Manny...
預訓練模型
項目截圖：
實測截圖：
一步一步教程：
1.下載這個項目：
https://github.com/Conchylicultor/DeepQA
2.下載訓練好的模型：
https://drive.google.com/file/d/0Bw-phsNSkq23OXRFTkNqN0JGUU0/view
（如果網址不能打開的話，今晚我會上傳到百度網盤，分享到：http://www.tensorflownews.com/）
3.解壓之后放在 項目 save 目錄下
如圖所示
4.復制 save/model-pretrainedv2/dataset-cornell-old-lenght10-filter0-vocabSize0.pkl 這個文件到 data/samples/
如圖所示：
5.在項目目錄執行一下命令：
python3 main.py --modelTag pretrainedv2 --test interactive
程序讀取了預訓練的模型之后，如圖：
聊天機器人資源合集
項目，語聊，論文，教程
https://github.com/fendouai/Awesome-Chatbot
更多教程：
http://www.tensorflownews.com/
DeepQA
備注：為了更加容易了解這個項目，說明部分翻譯了項目的部分 readme ，主要是介紹使用預處理數據來運行這個項目。