This repository contains code to derive the data generated by the pipeline described in the paper "Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summariz…

A library to conduct ranking experiments with transformers.

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

FRANK: Factuality Evaluation Benchmark

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

Coming soon! The datasets used for our paper will be available soon.

INCEpTION provides a semantic annotation platform offering intelligent annotation assistance and knowledge management.

Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (https://arxiv.org/abs/1902.02671)

Taxonomic Fragmentation of the NLI Task

Repository of my solutions to the problems of "Learning from Data"

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

My solutions to Kevin Murphy Machine Learning Book

Code for paper "Learning to Reweight Examples for Robust Deep Learning"

Methods of training NLP models to ignored biased strategies

Diagnostic tests for linguistic capacities in language models

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"

The Annotated Encoder Decoder with Attention

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Models, data loaders and abstractions for language processing, powered by PyTorch

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Python implementation of smooth optimal transport.

An experiment in procedural dance animation

Fashion 200K dataset used in paper "Automatic Spatially-aware Fashion Concept Discovery."

Sequence to Sequence Models with PyTorch

Synthesizing and manipulating 2048x1024 images with conditional GANs