This repository contains the source code of of the Nil-aware machine reading comprehension system, NAMANDA, which is published in EMNLP 2018.
- Python 2.7 (required for data preparation)
- Python 3.5
- Pytorch 0.2
The data preparation is described in prep-data/
. The source code for Nil-aware AMANDA is available in NAMANDA/
. It contains a seperate README file for further details.
If you use the source code or models from this work, please cite our paper:
@article{kundu2018namanda,
author = {Kundu, Souvik and Ng, Hwee Tou},
title = {A Nil-aware Answer Extraction Framework for Question Answering},
booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
year = {2018},
}
The code and models in this repository are licensed under the GNU General Public License Version 3. For commercial use of this code and models, separate commercial licensing is also available.
Some parts of the code are adapted from DrQA Repository.