This repository contains the datasets and code associated with the paper:

Charles Chen, and Razvan Bunescu. Context-Dependent Semantic Parsing over Temporally Structured Data. In NAACL 2019 (Oral Presentation) [Preprint] [CameraReady]

If you use our code in your research, please use the following BibTeX entry:

@inproceedings{chen-bunescu-2019-context,
  title={Context-Dependent Semantic Parsing over Temporally Structured Data},
  author={Chen, Charles and Bunescu, Razvan},
  booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)},
  publisher = {Association for Computational Linguistics},
  url = {https://www.aclweb.org/anthology/N19-1360},
  pages={3576--3585},
  year={2019}
}

• Python 2.7

• Tensorflow 0.9

• Numpy 1.14

• tqdm

• The folders correspond to the models used in our paper: SeqGen, SeqGenAtt2In, SPAAC-MLE, and SPAAC-RL.

• The folder data contains both Real Interaction and Artificial Interaction Datasets.

python main.py --phase='train'

OR

python main.py --phase='train' --load --model_file='pathtosavedmodel'

python main.py --phase='test' --load --model_file='pathtosavedmodel'

If you have any questions, please email me at lc971015@ohio.edu.

All the experiments in our paper are performed with an NVIDIA GeForce GTX 1080 GPU.