This is the work written by Ismael Villegas-Molina for the Applied NLP course taught by Ron Artstein.
Given a list of training data (with the input as two names and the output as the target full name), predict the full name of the first person in the input.
Very simple lemmatizer, which learns a lemmatization function from an annotated corpus.
Perform a Naive Bayes classification to identify hotel reviews as either truthful or deceptive, and either positive or negative. Use the word tokens as features for classification.
Perform a perceptron classification (vanilla and averaged) to identify hotel reviews as either truthful or deceptive, and either positive or negative. Uses the word tokens as features, or any other features devised from the text.
Homework 5: Hidden Markov Model Part-of-Speech Tagger
A Hidden Markov Model part-of-speech tagger for Italian and Japanese. The training data is provided tokenized and tagged; the test data will be provided tokenized, and the tagger will add the tags.