This repository contains assignments and slides for IDS703 Natural Language Processing at Duke.
In the NLP_hw
directory, there are 8 personal assignments.
- Regular Expression
- Write a regular expression that matches people’s full names
- Develop a regular expression that matches all gerunds within a text
- Spelling Correction
- Build a spelling corrector based on the Levenshtein distance
- N Gram Model
- Write a bare-bones Markov text generator
- POS Tagging
- Use the first 10k tagged sentences from the Brown corpus to generate the components of a part-of-speech hidden markov model
- Document Vectors
- Explore how term-document matrices and weightings can be used for docu- ment classification, including raw counts of terms, TF-IDF, TF-IDF variant
- RNN
- Construct, manually, a RNN structure and associated weights
- BRNN
- Construct, manually, a bidirectional RNN structure and associated weights
- NN Design
- Design a neural network that segments an English word into prefixes, root, and suffixes using a BIO labelling scheme.