search

aneesh-joshi / LSTM_POS_Tagger

A simple POS Tagger made using a Bidirectional LSTM using keras trained on the Brown Corpus
34 stars 19 forks source link

Dataset download script needed #12

Open aneesh-joshi opened 6 years ago

aneesh-joshi commented 6 years ago

https://github.com/aneesh-joshi/LSTM_POS_Tagger/blob/502b2637964be3ae872a8f2f012bb21306cc8057/make_glove_pickle.py#L11

LSTM postagger needs to make use of a glove data set. Due to github's limitation, it cannot be uploaded(it's over 1 GB)

We need to make a script which will automatically download the dataset. Ideally it should be in python to make it OS independent.

In bash, it would as simple as wget link

You can mostly use the code from here