Papers with Code 아카이브
document understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Document understanding involves document classification, layout analysis, information extraction, and DocQA.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
What Makes a Good Dataset for Symbol Description Reading?
PDFVQA: A New Dataset for Real-World VQA on PDF Documents
Is ChatGPT A Good Keyphrase Generator? A Preliminary Study
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding
Multimodal Tree Decoder for Table of Contents Extraction in Document Images
Unifying Vision, Text, and Layout for Universal Document Processing
ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information
VRDU: A Benchmark for Visually-rich Document Understanding
QueryForm: A Simple Zero-shot Form Entity Query Framework
Unimodal and Multimodal Representation Training for Relation Extraction
On Web-based Visual Corpus Construction for Visual Document Understanding
Transformer-based Approach for Document Understanding
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding
XDoc: Unified Pre-training for Cross-Format Document Understanding
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text
Improving Keyphrase Extraction with Data Augmentation and Information Filtering
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
DeeperDive: The Unreasonable Effectiveness of Weak Supervision in Document Understanding A Case Study in Collaboration with UiPath Inc
Understanding Long Documents with Different Position-Aware Attentions
Knowing Where and What: Unified Word Block Pretraining for Document Understanding
Towards Complex Document Understanding By Discrete Reasoning
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding
Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding
Test-Time Adaptation for Visual Document Understanding
RDU: A Region-based Approach to Form-style Document Understanding
Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness
MATrIX -- Modality-Aware Transformer for Information eXtraction
Unified Pretraining Framework for Document Understanding
End-to-end Document Recognition and Understanding with Dessurt
Multimodal Pre-training Based on Graph Attention Network for Document Understanding
Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.