The instructions and the data for the assignments will be uploaded to github at . To download the files to your machine, you will need to download and install git on your machine.  Git is a repository for the code that we will use this semester. Then you can clone the assignment files onto your machine.

git clone

This will create the folder cs114spring2015hw on your current directory.

When we have a new assignment or make an update or two to the code, you can download a new assignment or get an updated version of the code by running the following command in the directory where you clone the repository.

git pull origin master

This will synchronize what you have on your machine (your local repository) with what we have on the online repository.

List of assignments

There will be around seven assignments/problem sets for this class.

  1. Finite-state morphological parser
  2. N-gram language model
  3. Naive Bayes classifier
  4. Hidden Markov Model Part-of-Speech Tagger
  5. Probabilistic Syntactic Parser
  6. Distributional Lexical Semantics
  7. IBM Model 1 for Machine Translation


There will be one quiz in the midterm. There will be no final exam.

Problem sets are worth 75% of your grade.  The quiz is worth 15%.  Class participation is worth 10%.