word2vec

A simple Python program to generate (lowercase) embeddings, from someone (me) who really does not have much experience using Python.

Evaluation of various deep learning models for sentiment analysis You are given the reviews dataset. These are 194439 amazon reviews for cell phones and accessories taken from https://jmcauley.ucsd.edu/data/amazon/ Use the “reviewText” and “overall” fields from this file. The goal is to predict the rating given the review by modeling it as a multi-class classification problem. • Take the first 70% dataset for train, next 10% for validation/development, and remaining 20% for test. • Recurrent neural networks • RNNs: Train a single directional RNN with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set. • LSTMs: Train a single directional LSTM with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set. • BiLSTM: Train a single directional RNN with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set.

Machine Learning - Content Based Recommendation System

Extract most relevant Keywords from Web-page to the given list of Sentences or Words

The project uses natural language processing to automatically assess causal diagrams filled out by students based on semantic distance from the model causal diagram provided.

A repo for messing around with Google's word2vec model. Inspired by this computerphile video.

a Data Semantics Project

Simple text classification project on 20news data, using word embedding methods for text representation and supervised machine learning algorithms to classify.

This is the repository for my final year project. The title of the project is Deep Learning of Word Embeddings for semantic search.

Feature extractor to build an XML file with the required features for running ReelOut with the MSCoco Imageset.

Machine translation system using word2vec word embeddings and unsupervised learning to produce translations between languages. Developed as part of a summer internship program with QUT's partner university, Hokkaido University, in Japan.