Converting natural language instructions into its corresponding action sequence.
Here is the link to the base paper that is being referred.
Language used : Python 2.7
- Anaconda - Anaconda includes all the Python-related dependencies
- Theano - Computational graphs are built on Theano
- ArgParse - Command line parsing in Python
python train_model.py
python test_model.py -fp PATH
PATH stands for the path to the file model.pkl which lies within the tracks folder. This folder is created by the end of training.
The SAIL route instruction dataset has been downloaded from here.
The following code has been used for embedding sentences to vectors. It uses the skip-gram model.
This project is built using Hongyuan Mei's code as base.