Hebrew Diacritizer
MIT License
Training scripts and instructions how to reproduce our systems submitted to the NEWS 2018 Task on...
GLM (General Language Model)
Hercules: Attributable and Scalable Opinion Summarization (ACL 2023)
Benchmark Arabic text diacritization dataset
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
OCR-D wrapper for detectron2 based segmentation models
DCASE2024 Challenge Task 6 baseline system (Automated Audio Captioning)
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
We present NoticIA, a dataset consisting of 850 Spanish news articles featuring prominent clickba...
Basically SentEval with German language downstream tasks
Translation-over-Diacritization technique implementation
A centralized place for deep thinking code and experiments
An English-to-Cantonese machine translation model
Code for the paper "Factorising Meaning and Form for Intent-Preserving Paraphrasing", Tom Hosking...