Papers with Code 아카이브
Key Information Extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 6
- 보존된 평가 기록
- 20
Key Information Extraction (KIE) is aimed at extracting structured information (e.g. key-value pairs) from form-style documents (e.g. invoices), which makes an important step towards intelligent document understanding.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
DUBLIN -- Document Understanding By Language-Image Network
OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
Information Redundancy and Biases in Public Document Information Extraction Benchmarks
SIMARA: a database for key-value information extraction from full pages
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
Information Extraction from Documents: Question Answering vs Token Classification in real-world setups
A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images
PDFVQA: A New Dataset for Real-World VQA on PDF Documents
Form-NLU: Dataset for the Form Natural Language Understanding
DocILE Benchmark for Document Information Localization and Extraction
DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
PP-StructureV2: A Stronger Document Analysis System
Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
RDU: A Region-based Approach to Form-style Document Understanding
Relational Representation Learning in Visually-Rich Documents
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
Comparison of biomedical relationship extraction methods and models for knowledge graph creation
OCR-free Document Understanding Transformer
Entity Relation Extraction as Dependency Parsing in Visually Rich Documents
One-shot Key Information Extraction from Document with Deep Partial Graph Matching
MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations
Key Information Extraction From Documents: Evaluation And Generator
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents
Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
Spatial Dual-Modality Graph Reasoning for Key Information Extraction
ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.