Amanda Dawley Comp499 Capstone
Capstone Overview
Welcome to my Capstone research project for Computer Science (May 2023). A little about myself, I am a Computer Science and Mathematics double major at CI graduating this May! I have worked remotely for the past three years at an internet startup company. I worked solely on my capstone project with my company for the past few months. Using the data provided, I developed a Machine Learning Pipeline following the steps below to create a Named Entity Recognition (NER) using Stanford CoreNLP tools. The goal is to build and train a system to extract keywords for classification of articles.
Youtube Presentation Link
Click the link on the title above to view the ‘elevator pitch’ for this deliverable.
Poster Link
Click the link on the title above to be directed to a ‘view only’ digital version on the poster for this project.
MACHINE LEARNING PIPELINE OVERVIEW
- Assemble corpus of News Data to experiment and crawl the list of Real Simple Syndication (RSS) Publisher feeds
- Enhance documents retrieved from Publisher feeds, extract entities from the article text using Named Entity tools, and store/index enhanced article documents
- Establish term embeddings, query labeled datasets for Neural Network Classifier, and train a simple Neural Network
- Test the Classifier Model
