wh629 Goto Github PK

bds_project

c-bert

Attention-based models such as BERT have produced state-of-the-art performance on many NLP tasks. However, these models suffer from catastrophic forgetting (CF) in a continual setting. We hypothesize that utilizing meta-learning methodologies such as OML to further train BERT will help learn contextual representations that are more robust to CF.

convfinqa

Data and code for EMNLP 2022 paper "ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering"

cookiecutter-pypackage

Cookiecutter template for a Python package.

deep_learning

Collection of code used for NYU's Deep Learning course Spring 2020

deep_learning_dynamic_systems

Project report for deep learning on dynamic systems.

deep_learning_project

Repository for NYU Deep Learning SP20 Final Project

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

jiant

jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks.

jiant-1

The jiant toolkit for general-purpose text understanding models

llama

Inference code for LLaMA models

nli-variation-data

Human annotations for "Inherent Disagreements in Human Textual Inferences" paper

nyu-jiant

pytorch-deep-learning

Deep Learning (with PyTorch)

stereoset

StereoSet: Measuring stereotypical bias in pretrained language models

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

unqover

UnQovering Stereotyping Biases via Underspecified Questions - EMNLP 2020 (Findings)

wh629.github.io

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

wh629.github.io_change

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

wh629.github.io_whatatheme

A customizable Jekyll Portfolio theme which supports blogging.