Awesome

Code and sample data accompanying the paper Modeling Multi-turn Conversation with Deep Utterance Aggregation.

Dataset

We release E-commerce Dialogue Corpus, comprising a training data set, a development set and a test set for retrieval based chatbot. The statistics of E-commerical Conversation Corpus are shown in the following table.

The full corpus can be downloaded from https://drive.google.com/file/d/154J-neBo20ABtSmJDvm7DK0eTuieAuvw/view?usp=sharing.

Data template

label \t conversation utterances (splited by \t) \t response

Source Code

We also release our source code to help others reproduce our result

Instruction

Our code is compatible with <code>python2</code> so for all commands listed below python is <code>python2</code>

We strongly suggest you to use <code>conda</code> to control the virtual environment

• Install requirement

  <code>pip install -r requirements.txt</code>

• Pretrain word embedding

  <code>python train_word2vec.py ./ECD_sample/train embedding</code>

• Preprocess the data

  <code>python PreProcess.py --train_dataset ./ECD_sample/train --valid_dataset ./ECD_sample/valid --test_dataset ./ECD_sample/test --pretrained_embedding embedding --save_dataset ./ECD_sample/all</code>

• Train the model

  <code>bash train.sh</code>

Tips

If you encounter some cuda issues, please check your environment. For reference,

Theano 0.9.0
Cuda 8.0
Cudnn 5.1

Reference

If you use this code please cite our paper:

@inproceedings{zhang2018dua,
    title = {Modeling Multi-turn Conversation with Deep Utterance Aggregation},
    author = {Zhang, Zhuosheng and Li, Jiangtong and Zhu, Pengfei and Zhao, Hai},
    booktitle = {Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018)},
    pages={3740--3752},
    year = {2018}
}