Optical Character Recognition2020en

dart

Dataset from Papers With Code

Metrics:accuracy, cer, wer, f1

bert

#	Model	Score	Paper / Code	Date
1	T5B Baseline	0.951	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
2	FactT5B	0.951	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
3	FactJointGT	0.949	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
4	JointGT Baseline	0.949	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
5	GPT-2-Large (fine-tuning)	0.940	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
6	HTLM (fine-tuning)	0.940	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

bleu

#	Model	Score	Paper / Code	Date
1	T5B Baseline	48.47	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
2	FactT5B	48.37	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
3	JointGT Baseline	47.51	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
4	FactJointGT	47.39	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
5	HTLM (fine-tuning)	47.2	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
6	GPT-2-Large (fine-tuning)	47	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

bleurt

#	Model	Score	Paper / Code	Date
1	T5B Baseline	0.675	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
2	FactT5B	0.674	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
3	JointGT Baseline	0.673	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
4	FactJointGT	0.673	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
5	GPT-2-Large (fine-tuning)	0.400	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
6	HTLM (fine-tuning)	0.400	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

factspotter

#	Model	Score	Paper / Code	Date
1	FactT5B	97.6	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
2	FactJointGT	97.25	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
3	T5B Baseline	96.65	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
4	JointGT Baseline	95.86	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023

meteor

#	Model	Score	Paper / Code	Date
1	T5B Baseline	0.407	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
2	FactT5B	0.407	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
3	JointGT Baseline	0.404	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
4	FactJointGT	0.403	FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text GenerationCode	Oct 2023
5	HTLM (fine-tuning)	0.390	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
6	GPT-2-Large (fine-tuning)	0.390	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

mover

#	Model	Score	Paper / Code	Date
1	HTLM (fine-tuning)	0.510	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
2	GPT-2-Large (fine-tuning)	0.510	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021

ter

#	Model	Score	Paper / Code	Date
1	GPT-2-Large (fine-tuning)	0.460	HTLM: Hyper-Text Pre-Training and Prompting of Language Models	Jul 2021
2	HTLM (fine-tuning)	0.440	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: GPT-2-Large (fine-tuning), HTLM (fine-tuning)

Other Optical Character Recognition Datasets

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