feyzaakyurek

Afra Feyza Akyürek's starred repositories

gdrive

Google Drive CLI Client

Language:GoMIT8997 223 594

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Language:PythonApache-2.05153 32 52

promptsource

Toolkit for creating, sharing and using natural language prompts.

Language:PythonApache-2.02629 32 162

pytorch-meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Language:PythonMIT1965 44 141

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

Language:PythonApache-2.0915 15 63

openwebtext

Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.

Language:PythonGPL-3.0706 30 19

rome

Locating and editing factual associations in GPT (NeurIPS 2022)

Language:PythonMIT539 7 27

rfs

Language:Python367 8 38

prototypical-network-pytorch

A re-implementation of "Prototypical Networks for Few-shot Learning"

Language:PythonMIT298 6 18

GRaNDPapA

Generator of Rad Names from Decent Paper Acronyms

Language:Python280 3 1

LearningToCompare-Pytorch

Pytorch Implementation for CVPR2018 Paper: Learning to Compare: Relation Network for Few-Shot Learning

Language:Python250 10 13

StereoSet

StereoSet: Measuring stereotypical bias in pretrained language models

Language:PythonCC-BY-SA-4.0165 8 9

CEC-CVPR2021

Pytorch code for CVPR2021 paper "Few-Shot Incremental Learning with Continually Evolved Classifiers"

Language:PythonMIT147 6 21

inc-few-shot-attractor-public

Code for Paper "Incremental Few-Shot Learning with Attention Attractor Networks"

Language:PythonMIT118 7 10

CrossFit

Code for paper "CrossFit :weight_lifting:: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)

Language:Python102 7 8

timelms

TimeLMs: Diachronic Language Models from Twitter

Language:Jupyter Notebook100 3 1

continual-knowledge-learning

[ICLR 2022] Towards Continual Knowledge Learning of Language Models

Language:Python92 6 2

BBQ

Repository for the Bias Benchmark for QA dataset.

Language:PythonCC-BY-4.080 8 7

hurtlex

A multilingual lexicon of words to hurt.

Language:Python75 30

mukayese

State-of-the-art NLP tools for Turkish

Language:Jupyter NotebookMIT64 6 2

nlg-bias

Dataset + classifier tools to study social perception biases in natural language generation

Language:Python64 3 6

bold

Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper

NOASSERTION62 2 2

visual-clustering

Visual Clustering: Clustering Plotted Data by Image Segmentation

Language:PythonMIT24 20

indo-collex

Welcome to our repository! This repository hosts the data on "IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism" Research Paper published on ACL-IJCNLP 2021. We also provide the guideline on how we annotate the data.

MIT20 20