Computer Science 248/448

Homework

Fall 2019

• No late homework
• To get a class account, see https://accounts.csug.rochester.edu
• Turn in assignments using /u/cs248/TURN_IN from class account
• Programming assignments must be in python, and must run on class account

Homework 1, Due Th 9/5 11am

Implement the perceptron decoder using the data and weights given in /u/cs248/data/pos. Here is a simple test case. What is your accuracy on the test file?

Homework 2, Due Fri 9/13 5pm

Implement the perceptron training algorithm using HMM-based features and the data set from HW 1. Here is a simple test case. How does the accuracy on test data accuracy compare to HW 1?

Homework 3, Due Fri 10/18 5pm

Part 1: implement a viterbi cyk decoder using the following features:

• rule: (A,B,C)
• first word: (A, x_i+1 )
• last word: (A, x_k )

Here is a test case and description of the file format.

Part 2: implement perceptron training for this set of features. See test case.

Homework 4, Due Thu 10/24 beginning of class

Review problems handed out on 10/17.

Homework 5, Due Fri 11/22 5pm

Implement IBM Model 1, and plot log probability of training and test files in /u/cs248/data/mt. Here is a simple test case.

Homework 6, Due Tu 12/10 beginning of class

Review problems available on piazza.