GenTC: Generative Transformer via Contrastive Learning for Receipt Information Extraction
- 22 September 2023
- book chapter
- Published by Springer Nature
- p. 394-406
Abstract
No abstract availableKeywords
This publication has 22 references indexed in Scilit:
- LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding2021
- StructuralLM: Structural Pre-training for Form Understanding2021
- TRIE: End-to-End Text Reading and Information Extraction for Document Understanding2020
- LayoutLM: Pre-training of Text and Layout for Document Image Understanding2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction2019
- Integrating Coordinates with Context for Information Extraction in Document Images2019
- Chargrid: Towards Understanding 2D Documents2018
- FaceNet: A unified embedding for face recognition and clustering2015