google-research-datasets / vrdu
We identify the desiderata for a comprehensive benchmark and propose Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types, complex templates, and diversity of layouts within a single document type.
☆79Updated 2 years ago
Alternatives and similar repositories for vrdu:
Users that are interested in vrdu are comparing it to the libraries listed below
- ReadingBank: A Benchmark Dataset for Reading Order Detection☆104Updated 7 months ago
- InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)☆160Updated 9 months ago
- ☆32Updated 11 months ago
- The code related to the baselines from NeurIPS 2021 paper "DUE: End-to-End Document Understanding Benchmark."☆36Updated 2 years ago
- An unofficial Implementation of DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents☆36Updated last year
- Example codebase for fine-tuning layoutLMv3 on DocVQA☆50Updated 2 years ago
- Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.☆185Updated 3 weeks ago
- Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.☆120Updated last year
- Publicly released code for the LAMBERT model☆103Updated 3 years ago
- DocILE: Document Information Localization and Extraction Benchmark☆123Updated 10 months ago
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆42Updated 11 months ago
- ☆43Updated 2 years ago
- Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files☆137Updated last year
- ☆57Updated 3 years ago
- CTE: Contextualized Table Extraction Dataset☆17Updated 2 years ago
- ☆158Updated 2 years ago
- OCR Annotations from Amazon Textract for Industry Documents Library☆102Updated 2 years ago
- ☆22Updated last year
- The WordScape repository contains code for the WordScape pipeline to create datasets to train document understanding models.☆35Updated last year
- Official implementation for Dessurt☆58Updated 2 years ago
- XFUND: A Multilingual Form Understanding Benchmark☆198Updated 2 years ago
- DocLLM: A layout-aware generative language model for multimodal document understanding☆123Updated last year
- Code for ICPR2022 paper: "Graph Neural Networks and Representation Embedding for table extraction in PDF Documents"☆35Updated last year
- Index of URLs to pdf files all over the internet and scripts☆23Updated last year
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆76Updated 5 months ago
- An unofficial Pytorch implementation of ERNIE-Layout which is originally released through PaddleNLP.☆104Updated last year
- Streamlit Named Entity Recognition (NER) annotation custom component☆38Updated 2 years ago
- ☆243Updated 2 years ago
- Datasets and Evaluation Scripts for CompHRDoc☆33Updated last month
- ☆62Updated last year