我用tensorflow實現的“一個神經聊天模型”:一個基於深度學習的聊天機器人

磐石001發表於2017-09-05

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).
它使用了迴圈神經網路(seq2seq 模型)來進行句子預測。它是用 python 和 TensorFlow 開發。

程式的載入主體部分是參考 Torch的 neuralconvo from macournoyer.

現在, DeepQA 支援一下對話語料:
* 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

這個程式需要一下依賴(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資料讓 nltk 正常工作。

python3 -m nltk.downloader punkt

Cornell 資料集已經包括了。其他的資料集檢視 readme 檔案到他們所在的資料夾。 (在 data/).

網站介面需要一些附加的包:

  • django (tested with 1.10)
  • channels
  • Redis (see here)
  • asgi_redis (at least 1.0)

Docker 安裝也是支援的,更多詳細的教程參考 here.

執行

聊天機器人

訓練這個模型,直接執行 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 --saveEvery option.
* --filterVocab 20 or --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 --createDataset if this is the only action you want to perform).

To visualize the computational graph and the cost with TensorBoard, just run tensorboard --logdir save/.

預設的這個網路架構是一個標準的 encoder/decoder 有兩個 LSTM layers (隱藏層大小 256) ,然後 vocabulary 的 embedding size 是 32.這個網路用 ADAM 訓練。最大的句子長度設定為 10個單詞,但是可以增加。

結果

當然,這個網路並不會很擅長聊天:

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.

這裡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

專案截圖:

chatbot_miniature.png

實測截圖:

Screenshot from 2017-09-05 14-47-52.png

一步一步教程:

1.下載這個專案:
https://github.com/Conchylicultor/DeepQA
2.下載訓練好的模型:
https://drive.google.com/file/d/0Bw-phsNSkq23OXRFTkNqN0JGUU0/view
(如果網址不能開啟的話,今晚我會上傳到百度網盤,分享到:http://www.tensorflownews.com/
3.解壓之後放在 專案 save 目錄下
如圖所示

Screenshot from 2017-09-05 14-52-13.png

4.複製 save/model-pretrainedv2/dataset-cornell-old-lenght10-filter0-vocabSize0.pkl 這個檔案到 data/samples/

如圖所示:

Screenshot from 2017-09-05 14-55-00.png

5.在專案目錄執行一下命令:

python3 main.py --modelTag pretrainedv2 --test interactive

程式讀取了預訓練的模型之後,如圖:

Screenshot from 2017-09-05 14-57-14.png

聊天機器人資源合集

專案,語聊,論文,教程
https://github.com/fendouai/Awesome-Chatbot

更多教程:

http://www.tensorflownews.com/

DeepQA

https://github.com/Conchylicultor/DeepQA

備註:為了更加容易瞭解這個專案,說明部分翻譯了專案的部分 readme ,主要是介紹使用預處理資料來執行這個專案。


相關文章