SOTAVerified

Key Information Extraction

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.

Papers

Showing 4150 of 74 papers

TitleStatusHype
Comparison of biomedical relationship extraction methods and models for knowledge graph creation0
Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use0
See then Tell: Enhancing Key Information Extraction with Vision Grounding0
SIMARA: a database for key-value information extraction from full pages0
Spatial Dual-Modality Graph Reasoning for Key Information Extraction0
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents0
ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents0
ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents0
VKIE: The Application of Key Information Extraction on Video Text0
"What is the value of templates?" Rethinking Document Information Extraction Datasets for LLMs0
Show:102550
← PrevPage 5 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RORE (GeoLayoutLM)F198.52Unverified
2GeoLayoutLMF197.97Unverified
3LayoutLMv3 LargeF197.46Unverified
4LayoutMask (large)F197.19Unverified
5LayoutMask (base)F196.99Unverified
6TPP (LayoutMask)F196.92Unverified
7LILTF196.07Unverified
8LayoutLMv2LARGEF196.01Unverified
9LayoutLMv2BASEF194.95Unverified
#ModelMetricClaimedVerifiedStatus
1LayoutLMv2LARGE (Excluding OCR mismatch)F197.81Unverified
2RORE (GeoLayoutLM)F196.97Unverified
3LayoutLMv2LARGEF196.61Unverified
4LayoutLMv2BASEF196.25Unverified
5ChatGPT 3.5 SpatialFormatAccuracy77Unverified
#ModelMetricClaimedVerifiedStatus
1LayoutLMv2LARGEF185.2Unverified
2LayoutLMv2BASEF183.3Unverified
3LAMBERT (75M)F180.42Unverified
#ModelMetricClaimedVerifiedStatus
1DANF1 (%)95.05Unverified