Efficient and clean PyTorch reimplementation of "End-to-end Neural Coreference Resolution" (Lee et al., EMNLP 2017).

Implementations of basic machine learning algorithms using only numpy, pandas, and matplotlib.

Code for reproducing the results of "Evaluating Generative Adversarial Networks on Explicitly Parameterized Distributions" (O'Brien et al., NeurIPS 2018).

A sample of selected papers that I have authored or co-authored.

Unsupervised methods for analysis of conversational transcripts

Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN

Language modeling on the Penn Treebank (PTB) corpus using a trigram model with linear interpolation, a neural probabilistic language model, and a regularized LSTM.

Neural and nonneural text segmentation methods.

Neural machine translation on the IWSLT-2016 dataset of Ted talks translated between German and English using sequence-to-sequence models with/without attention and beam search.

Neural sentiment classification of text using the Stanford Sentiment Treebank (SST-2) movie reviews dataset, logistic regression, naive bayes, continuous bag of words, and multiple CNN variants.

Offline and online (i.e., real-time) annotated clustering methods for text data.

LexRank for ranking documents containing some keyword or keyphrase using cosine similarities of either naive, tfidf, or idf-modified-cosine. Non-query ranking also supported.

Methods in numerical analysis. Includes: Lagrange interpolation, Chebyshev polynomials for optimal node spacing, iterative techniques to solve linear systems (Gauss-Seidel, Jacobi, SOR), SVD, PCA, …

Visualizations that I created while at Clemson University developing methods for the visualization of light detection and ranging (LIDAR) data.

Visually explore how the meaning of words changes over time.

Solutions that I have coded to a variety of projecteuler.net problems in Python and MATLAB.

A rule-based system to compress simple sentence using nltk