CS 288: Statistical Natural Language Processing

CS 288: Statistical Natural Language Processing, Fall 2014

Assignment 1: Language Modeling
Due September 12

    Project description
    code1.tar.gz: the Java source code provided for this project
    data1.tar.gz: the data sets used in this assignment

Submit your project here

Updates

9/8/14: The normalization spot-check no longers sums over the start symbol as a possible word to generate.
8/31/14: There was a bug in the testing harness causing translation not to be carried out for the STUB and UNIGRAM language models. Please re-download code1.tar.gz (but the data is unchanged).