This repo contains python tutorials for basic text processing in Python, including standard NLP pipelines with Stanford CoreNLP and Spacy. All the notebooks were written in Google Colab. This is meant to be an introductory course for people with no prior knowledge of Python. Although, some basic coding background could be useful.
This tutorial is organized by FACTS.lab (http://factslab.io/)
Instructor: Siddharth Vashishtha
The topics covered are listed below:
Google Colab Link: https://bit.ly/2kDLgv9 (Both 1 and 2)
Topics
- Basic datatypes and operations in Python
- If-else statements
- Loops
Topics
- List comprehensions
- Defining Functions
- Regular expressions (regex)
Google Colab Link: https://bit.ly/2kvyvms
Topics
- Review tokenization issues
- Tokenization, Sentence separation (corenlp, spacy)
- Lemmatization (corenlp, spacy)
- Reading corpuses
- Plotting unigram counts
- Zipfian distribution
Google Colab Link: https://bit.ly/2mi0KW7
Topics
- Google ngram viewer
- Constituency Parsers
- Dependency Parsers
- Tree searching
Google Colab Link: https://bit.ly/2lUP3EK
Topics
- Semantic Role Labelling
- PropBank, FrameNet
- PredPatt
- Semantic Parsers
- Other tasks: WSD, Coreference resolution
Timings: 6.00 PM - 7.30 PM
Venue: Genesee 325, University of Rochester