akoksal

Abdullatif Köksal's starred repositories

dalle-mini

DALL·E Mini - Generate images from a text prompt

Language:PythonApache-2.014742 113 155

cleanlab

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Language:PythonAGPL-3.09365 89 363

TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

Language:PythonMIT2886 38 275

stylized-neural-painting

Official Pytorch implementation of the preprint paper "Stylized Neural Painting", in CVPR 2021.

Language:PythonCC0-1.01561 29 61

simalign

Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

Language:PythonMIT345 10 33

llm-seminar

Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)

308 180

BalancedLossNLP

Language:Jupyter NotebookNOASSERTION125 6 13

Glot500

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023

Language:PythonNOASSERTION96 8 8

GlotLID

GlotLID: Language Identification with Support for More Than 2000 Labels -- EMNLP 2023

Language:PythonApache-2.084 4 4

neural-painters-x

Neural Paiters

Language:Jupyter NotebookMIT78 8 1

turkish

Dart library for some Turkish language specific operations.

Language:DartMIT41 4 1

RELX

The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification, EMNLP-Findings 2020.

Language:PythonMIT19 20

BoAT

Boğaziçi University Annotation Tool for Dependency Parsing

Language:Python15 6 30

GlotScript

GlotScript: A Resource and Tool for Low Resource Writing System Identification -- LREC 2024

Language:PythonMIT13 10

parcoure

ParCourE - Parallel Corpus Explorer

Language:PythonMIT12 40

mPLM-Sim

mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models

Language:PythonNOASSERTION10 80

graph-align

code for EMNLP graph align paper

Language:Python9 30

address-ner-training

Language:Python800

xtremespeech

Code and data for our ACL 2022 Findings paper, "Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments"

Language:Python7 30

GlotWeb

GlotWeb: Web Indexing for Low-Resource Languages -- under construction.

Language:PythonCC0-1.05 2 2

Taxi1500

Language:PythonApache-2.05 5 2

CaMEL

Language:Jupyter NotebookMIT500

MemLLM

Language:Python400

TurkishMMLU

400

ColexificationNet

Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs

Language:Jupyter Notebook3 50

GlotStoryBook

Children StoryBooks for 180 langauges.

Language:Jupyter NotebookCC0-1.03 3 2

lohoravens-webpage

Language:JavaScript2 80

billiard-ball-detection

Language:MATLAB200

uai2022-intervention-estimation-latents

Codebase for paper Intervention Target Estimation in the Presence of Latent Variables (UAI 2022))

Language:R100

garantihackathon2015-mandalina

Language:Java100