The solution is placed at GitHub, you could fork or download it here.
For now it is a Telegram bot, but it could easily be switched to our server by providing
base_url parameter in telegram bot initialisation here. More information about parameters of telegram bot framework could be found here.
The solutaion is based on two papers:
Neural Question Generation from Text: A Preliminary Study https://arxiv.org/abs/1704.01792
Bidirectional Attention Flow for Machine Comprehension https://arxiv.org/abs/1611.01603
We are using forked repo of Allen AI2 bi-att-flow: https://github.com/allenai/bi-att-flow
sudo apt-get install libzmq3-dev
brew install zeromq --with-libpgm
Python packages will be installed by
It you’re using git version 1.6.5+, you could clone with dependencies:
git clone --recursive firstname.lastname@example.org:MIPTDeepLearningLab/ConvAI-baseline.git
If you’re using earlier versions of git, or if you have the repo downloaded without
--recursive, you should clone dependency repos additionally:
git clone email@example.com:MIPTDeepLearningLab/ConvAI-baseline.git cd ConvAI-baseline git submodule update --init --recursive
Setup will download docker images, models and data files, so you have no need to download any of that by yourself.
stopall is stopping all the services after the killing the bot, while
stop just kills the bot only. The
restarall is using
stopall instead of simple