Optical Character Recognition2020en

webnlg-(all)

Dataset from Papers With Code

Metrics:accuracy, cer, wer, f1

bleu

#	Model	Score	Paper / Code	Date
1	HTLM (fine-tuning)	55.6	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
2	GPT-2-Large (fine-tuning)	55.5	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

meteor

#	Model	Score	Paper / Code	Date
1	HTLM (fine-tuning)	0.420	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
2	GPT-2-Large (fine-tuning)	0.420	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

ter

#	Model	Score	Paper / Code	Date
1	GPT-2-Large (fine-tuning)	0.420	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
2	HTLM (fine-tuning)	0.400	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

Related Papers1

HTLM: Hyper-Text Pre-Training and Prompting of Language Models

Jul 2021Models: HTLM (fine-tuning), GPT-2-Large (fine-tuning)

Other Optical Character Recognition Datasets

scut-ctw1500 mpqa cnn-/-daily-mail icdar2013 SROIE KITAB-Bench ThaiOCRBench PolEval 2021 OCR IMPACT-PSNC wikibio

webnlg-(all) Benchmark - Optical Character Recognition | CodeSOTA