BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Paper • 2108.04539 • Published
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModel
processor = AutoProcessor.from_pretrained("jinho8345/bros-base-uncased")
model = AutoModel.from_pretrained("jinho8345/bros-base-uncased", device_map="auto")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This is a converted version of bros-base-uncased with conversion script
BROS
GitHub: https://github.com/clovaai/bros
Introduction
BROS (BERT Relying On Spatiality) is a pre-trained language model focusing on text and layout for better key information extraction from documents.
Given the OCR results of the document image, which are text and bounding box pairs, it can perform various key information extraction tasks, such as extracting an ordered item list from receipts.
For more details, please refer to our paper:
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Teakgyu Hong, Donghyun Kim, Mingi Ji, Wonseok Hwang, Daehyun Nam, Sungrae Park
AAAI 2022 - Main Technical Track
Pre-trained models
| name | # params | Hugging Face - Models |
|---|---|---|
| bros-base-uncased (this) | < 110M | naver-clova-ocr/bros-base-uncased |
| bros-large-uncased | < 340M | naver-clova-ocr/bros-large-uncased |
- Downloads last month
- 12,778
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jinho8345/bros-base-uncased")