varepsilon

stable-diffusion

A latent text-to-image diffusion model

langchain

⚡ Building applications with LLMs through composability ⚡

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

powerlevel10k

A Zsh theme

iodine

Official git repo for iodine dns tunnel

YaLM-100B

Pretrained language model with 100B parameters

SDV

Synthetic data generation for tabular data

portfolio

Track and evaluate the performance of your investment portfolio across stocks, cryptocurrencies, and other assets.

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

bleurt

BLEURT is a metric for Natural Language Generation based on transfer learning.

aclpubcheck

Tools for checking ACL paper submissions

convai

ua-gec

UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language

PIE

Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)

yolopandas

C4_200M-synthetic-dataset-for-grammatical-error-correction

This dataset contains synthetic training data for grammatical error correction. The corpus is generated by corrupting clean sentences from C4 using a tagged corruption model. The approach and the dataset are described in more detail by Stahlberg and Kumar (2021) (https://www.aclweb.org/anthology/2021.bea-1.4/)

m2scorer

MaxMatch (M^2) Scorer - Evaluation program for grammatical error correction systems.

e2e-metrics

E2E NLG Challenge Evaluation metrics

UNION

UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation

yandex-tank

Technical fork. All issues, requests etc. should be done in yandex/yandex-tank

X-MAML

Code base for " Zero-Shot Cross-Lingual Transfer with Meta Learning" papaer

discofuse

FairRecSys

[Official Codes] Experiments on Generalizability of User-Oriented Fairness in Recommender Systems (SIGIR 2022)

user-satisfaction-simulation

"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems" in SIGIR'21

CWEB

ZEST

clse

The Corpus of Linguistically Significant Entities (CLSE) is a dataset of named entities annotated by linguist experts. It includes 34 languages and covers 74 different semantic types to support various applications from airline ticketing to video games. The aim of the corpus is to facilitate the creation of more linguistically diverse NLG datasets.

RULEC-GEC

RULEC-GEC is a dataset of sentences written by learners of Russian and annotated for mistakes.

scai-conf.github.io

telegram-bot-help-ua-ch

Telegrom bot that helps war in Ukraine refugees who seek information about a refuge in Switzerland.