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.
Class-Agnostic Region-of-Interest Matching in Document Images
Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Models
Emergency Communication: OTFS-Based Semantic Transmission with Diffusion Noise Suppression
KIEval: Evaluation Metric for Document Key Information Extraction
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy
"What is the value of {templates}?" Rethinking Document Information Extraction Datasets for LLMs
GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network
See then Tell: Enhancing Key Information Extraction with Vision Grounding
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents
Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding
Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use
XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser
KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents
A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents
RealKIE: Five Novel Datasets for Enterprise Key Information Extraction
OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition
TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
Construction of a Syntactic Analysis Map for Yi Shui School through Text Mining and Natural Language Processing Research
LAPDoc: Layout-Aware Prompting for Documents
Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations
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
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation
GenKIE: Robust Generative Multimodal Document Key Information Extraction
VKIE: The Application of Key Information Extraction on Video Text
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction
Data Efficient Training of a U-Net Based Architecture for Structured Documents Localization
AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts
End-to-End Document Classification and Key Information Extraction using Assignment Optimization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.