This is the official code for the Microsoft's submission of SDNet model to CoQA leaderboard. It is implemented under PyTorch framework. The related paper to cite is:
SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering, by Chenguang Zhu, Michael Zeng and Xuedong Huang, at https://arxiv.org/abs/1812.03593.
For usage of this code, please follow Microsoft Open Source Code of Conduct.
main.py: the starter code
Models/
Utils/
Requirement: PyTorch 0.4.1, spaCy 2.0.16. The docker we used is available at dockerhub: https://hub.docker.com/r/zcgzcgzcg/squadv2/tags. Please use v3.0 or v4.0.
Your directory should look like this:
Then, execute python main.py train path_to_coqa/conf
.
If you run for the first time, CoQAPreprocess.py will automatically create folders conf~/spacy_intermediate_features~ inside coqa to store intermediate tokenization results, which will take a few hours.
Every time you run the code, a new running folder run_idx will be created inside coqa/conf~, which contains running logs, prediction result on dev set, and best model.
If you have any questions, please contact Chenguang Zhu, chezhu@microsoft.com