This repository contains various NLP projects that I have worked on, including some that were a part of my B.Sc. in Computer Science at the Hebrew University of Jerusalem. The projects utilize various machine learning tools and models, and covers a range of NLP tasks, such as sentiment analysis, text classification, named entity recognition, and more.
- Sentiment Analysis of Movie Reviews: This project compares the performance of 3 different models, including Bi-directional LSTM, on a stanfordSentimentTreebank dataset
and determines which one is the most effective at predicting the sentiment of the given sentences.
for more information, seesentiment_analysis
package. - Pretraining and Transformers: This project involves experimenting with simple Transformer models to perform text classification on a subset of the 20newsgroups dataset. The goal is to compare the performance of three different models: two common uses of Transformers and a simple linear model. The project involves running and evaluating a Log-linear classifier, finetuning a Transformer model, and running zero-shot classification.
for more information, seepretraining_transformers
package.
Each project is contained within its own directory, along with a README file that provides more details about the project and how to run it. Simply navigate to the project directory that you're interested in and follow the instructions in the README file to get started.
If you would like to contribute to any of the projects in this repository, feel free to submit a pull request. I am always open to collaboration and feedback.