ovshake / np_analysis

Adversarial attacks generated for the ACL paper "Did the Model Understand the Question?"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Analysis of Neural Programmer

Code to replicate the results from the ACL 2018 paper "Did the Model Understand the Question?".

Based on the implementation of Neural Programmer from tensorflow/models

Download and extract the data from here.

Download and extract a pretrained model, copy of ACL 2018 paper results, and perturbed version of WikiTableQuestions from this Dropbox folder

Unzip the downloaded files in the root folder of the git repo and the code should work out-of-the-box.

For questions, please contact Pramod Kaushik Mudrakartapramodkm@uchicago.edu

Cite

Mudrakarta, Pramod Kaushik, Ankur Taly, Mukund Sundararajan, and Kedar Dhamdhere. "Did the Model Understand the Question?." arXiv preprint arXiv:1805.05492 (2018).

@article{mudrakarta2018did,
  title={Did the Model Understand the Question?},
  author={Mudrakarta, Pramod Kaushik and Taly, Ankur and Sundararajan, Mukund and Dhamdhere, Kedar},
  journal={arXiv preprint arXiv:1805.05492},
  year={2018}
}

About

Adversarial attacks generated for the ACL paper "Did the Model Understand the Question?"

License:Apache License 2.0


Languages

Language:Jupyter Notebook 53.4%Language:Python 46.6%