This is the homework repository for LING570: Shallow techniques for NLP
A simple word tokenizer using Regex
DFA and NFA acceptors
FSA acceptor using Viterbi algorithm
An expanded FSM given a lexicon and morphotactic rules expressed by an FSA
N-gram language models
A 2-gram HMM and a 3-gram HMM
Viterbi algorithm for HMM
A feature vector builder which reads raw text data and generates feature vectors.
A system which reads and processes text data, generates features used in MaxEnt.