Reading Order Detection
2개 벤치마크 · 논문 9편 · 이 태스크의 논문 보기 →
Benchmarks
ROOR
ReadingBank
Most implemented
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
LayoutReader: Pre-training of Text and Layout for Reading Order Detection
Papers
Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers
Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts make computational access to these materials both challenging and limited. We present the Institutional …
Reading Order DetectionFocalOrder: Focal Preference Optimization for Reading Order Detection
Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we chall…
Reading Order DetectionDREAM: Document Reconstruction via End-to-end Autoregressive Model
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ …
Document Layout AnalysisReading Order DetectionInfinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptab…
Document AIdocument understandingLanguage ModelingLanguage Modelling+4Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Previous works typically formulated layout…
document understandingEntity LinkingKey Information ExtractionReading Order Detection+2Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs), in which named entity recognition (NER) is treated as a sequence-labeling task of p…
Entity LinkingKey Information ExtractionKey-value Pair Extractionnamed-entity-recognition+9