https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout
공식 코드ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/PaddlePaddle/PaddleOCR
공식 코드https://github.com/ZeningLin/PEneo
공식 코드https://github.com/adlnlp/form_nlu
공식 코드Form-NLU: Dataset for the Form Natural Language Understanding
https://github.com/alibabaresearch/advancedliteratemachinery
공식 코드GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
https://github.com/andreagemelli/doc2graph
공식 코드Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
https://github.com/applicaai/lambert
공식 코드LAMBERT: Layout-Aware (Language) Modeling for information extraction
https://github.com/caop-kie/GraphRevisedIE
공식 코드GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network
https://github.com/chongzhangFDU/ROOR
공식 코드Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
https://github.com/chongzhangfdu/tpp
공식 코드Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
https://github.com/clovaai/bros
공식 코드https://github.com/clovaai/donut
공식 코드https://github.com/glasgow-ai4biomed/genkie
공식 코드GenKIE: Robust Generative Multimodal Document Key Information Extraction
https://github.com/ibm/kvp10k
공식 코드KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents
https://github.com/jpwang/lilt
공식 코드https://github.com/lamps-lab/AutoMeta
공식 코드https://github.com/laytextllm/laytextllm
공식 코드https://github.com/mainlp/ner-disagreements
공식 코드Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations
https://github.com/microsoft/unilm
공식 코드LayoutLM: Pre-training of Text and Layout for Document Image Understanding
https://github.com/microsoft/unilm/tree/master/layoutlmv3
공식 코드LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
https://github.com/microsoft/unilm/tree/master/layoutxlm
공식 코드LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
https://github.com/neeleshkshukla/dosa
공식 코드DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop
https://github.com/obensch/DocumentInformationExtraction
공식 코드Key Information Extraction From Documents: Evaluation And Generator
https://github.com/open-mmlab/mmocr
공식 코드Spatial Dual-Modality Graph Reasoning for Key Information Extraction
https://github.com/pd162/roi-matching
공식 코드Class-Agnostic Region-of-Interest Matching in Document Images
https://github.com/rossumai/docile
공식 코드DocILE Benchmark for Document Information Localization and Extraction
https://github.com/scut-dlvclab/gpt-4v_ocr
공식 코드Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation
https://github.com/seif-lat/bias-study-funsd-sroie
공식 코드Information Redundancy and Biases in Public Document Information Extraction Benchmarks
https://github.com/update-for-integrated-business-ai/amurd
공식 코드AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification
https://github.com/wenwenyu/PICK-pytorch
공식 코드https://github.com/yuliang-liu/monkey
공식 코드TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
https://github.com/yuliang-liu/multimodalocr
공식 코드OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
https://github.com/zhbuaa0/layoutlmft
공식 코드XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser
https://github.com/zhbuaa0/xformparser
공식 코드XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser
https://github.com/2023-MindSpore-1/ms-code-2/tree/main/OCRNet
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bros
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.