Natural Language Processing and Deep Learning

These NLP and DL projects were completed as part of the MSDS program at the University of Texas at Austinl

Analysis and Fine-Tuning of an SNLI Trained Model using Static Dataset Cartography and Out of Domain Datasets

An ELECTRA-small Natural Language Inference (NLI) model was trained based on the Stanford NLI dataset. Two methods are proposed for model improvement: 1) static dataset cartography and 2) training on Out of Domain (OOD) datasets. It is shown that training on ambiguous datasets offers the greatest advantage in fine tuning of the baseline model. Furthermore, training on small number of OOD examples can cause drastic increase in model performance on overall OOD datasets.

A State-Based Agent for Automated Goal Scoring in SuperTuxKart Ice Hockey

This paper presents an agent that was trained using imitation learning on video game state data with the objective to automate goal scoring in SuperTuxKart Ice Hockey. A four-layer deep neural network was used to train the model on training data obtained from the teacher agent. It is shown that the trained agent closely matches the agent that it was trained to imitate (teacher), scoring 84% as many goals as the teacher agent..