Skip to content

Latest commit

 

History

History
53 lines (38 loc) · 1.69 KB

README.md

File metadata and controls

53 lines (38 loc) · 1.69 KB
Raw

ChainsofReasoning

Code for paper Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

##Dependencies

Instructions for running the code

Data

Get the data from here. (Note: This might change soon, as I will release an updated version of the dataset)

To get the correct format to run the models,

cd data
/bin/bash make_data_format.sh <path_to_input_data> <output_dir>

For example you can run,

cd data
/bin/bash make_data_format.sh examples/data_small_input examples/data_small_output

Model

To start training, first checkout run_scripts/config.sh. This defines all the hyperparams and other inputs to the network. After specifying model parameters, to start training run,

cd run_sripts
/bin/bash train.sh ./config.sh

Path Query Experiment on WordNet (Sec 5.5 of the paper)

Checkout the instructions of the readme page in wordnet_experiment/README.md.

GPU/CPU settings

Set gpu_id=0 in run_scripts/config.sh to enable GPU training using CUDA. Set gpu_id=-1 in run_scripts/config.sh to disable GPU training.

Changelog

  • Aug 7 2017: Released the dataset used for the EACL paper. I apologize for the delay.
  • Mar 29 2017: added test scripts.

Contact:

Feel free to email me with any questions you have at rajarshi@cs.umass.edu