Papers with Code 아카이브
Key-value Pair Extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 20
Extract key-value pairs from a form-like document.
A prediction is considered TP if the predicted key and value contents match the ground truths. Key-value pair F1-score is employed as the metric.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images
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
OCR-free Document Understanding Transformer
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.