Source code and documentation for research project on hedges

• Author: Javier Llaca
• Speech Lab, Department of Computer Science, Columbia University

This repository contains programs for

1. Extracting data from a corpus and preparing it for crowdsourced annotation
2. Training a classifier on the annotated data

Java Packages:

• Apache OpenNLP
• Apache Commons CSV

Python Modules

• NLTK
• scikit-learn