Overview

Download the assignment file assignment2.zip.

This assignment consists of a part on word vectors and a part on RNNs:

• word vectors (inside wordvec)
  • imdb_glove.ipynb: train glove and LSA, test on supervised sentiment classification
  • commoncrawl_glove.ipynb: evaluate word representations

The respective notebooks contain more detailed instructions and inline questions.

After you downloaded and unzipped assignment2.zip:

• run jupyter notebook in the assignment folder

Submitting your work:

Once you are done working run the collectSubmission.sh script; this will produce a file called assignment2.zip. Submit this to the class Dropbox.

The written part should be included, either in the notebook, or as a separate file. If you worked with a partner, please submit one answer (unless you substantially disagree on it). Include the ids of both partners.

Download data:

Run the git clone https://github.com/cos495nlp/data from the assignment2 directory.

Start IPython:

You should start the IPython notebook server from the assignment2 directory, with the jupyter notebook command.