UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

XLNet for generating language.

code/data for "Jointly Optimizing Diversity and Relevance in Neural Response Generation" (Gao et al., NAACL'19)

Code for "Aligning Linguistic Words and Visual Semantic Units for Image Captioning", ACM MM 2019

Design and build a chatbot using data from the Cornell Movie Dialogues corpus, using Keras

Text generation workbench, starting with Markov Chains. Play with text! Python, with a CLI and local Flask app.

LM pretraining for generation, reading list, resources, conference mappings.

Script Buddy v2 is a film script text generation tool built using film scripts from the world's most popular film scripts.

This is the final project for Multimedia course CSE6501

Data and code for Kang et al., EMNLP 2019's paper titled "Linguistic Versus Latent Relations for Modeling a Flow in Paragraphs"

Context Free Grammar (CFG) Parser & Sentence Generator

List of Awesome Papers in NLP/Generative Modeling/Others

A set of scripts meant to intake a dictionary file of languages and generate fake words that look like they belong in that language. Included is also a password generator that can use these fake words to create easy-to-remember pronounceable passwords.

Name your own dinosaurs

Natural language projects, mainly just word counting and sorting algorithms

Final project for CPSC 185: Control, Privacy, and Technology, spring '17.

Keras implementation of the Delete, Retrieve, Generate sentiment and style transfer research

All codes and data used for NLP project