https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/LayoutLLM
공식 코드LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/BangLiu/ArticlePairMatching
공식 코드Matching Article Pairs with Graphical Decomposition and Convolutions
https://github.com/DS3Lab/WordScape
공식 코드https://github.com/Euphoria16/DocMark
공식 코드Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
https://github.com/HCIILAB/EPHOIE
공식 코드Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution
https://github.com/JbRemy/Cahan
공식 코드Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding
https://github.com/JiuTian-VL/TokenCorrCompressor
공식 코드Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/tutorials/Certification_Trainings/Healthcare
공식 코드Improving Clinical Document Understanding on COVID-19 Research with Spark NLP
https://github.com/Jordy-VL/multi-modal-early-exit
공식 코드Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting
https://github.com/Line-Kite/HGALayoutLM
공식 코드Hypergraph based Understanding for Document Semantic Entity Recognition
https://github.com/MohamedAliRashad/arabic-nougat
공식 코드Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction
https://github.com/NVlabs/FRAG
공식 코드FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding
https://github.com/NilBiescas/GeoContrastNet
공식 코드GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding
https://github.com/PaddlePaddle/PaddleMIX
공식 코드PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout
공식 코드ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
https://github.com/PaddlePaddle/PaddleOCR
공식 코드https://github.com/PrimerAI/sdu-data
공식 코드Primer AI's Systems for Acronym Identification and Disambiguation
https://github.com/adlnlp/3mvrd
공식 코드3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
https://github.com/ag2ai/simpledoc
공식 코드SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
https://github.com/ai-application-and-integration-lab/ridge
공식 코드Relation-Rich Visual Document Generator for Visual Information Extraction
https://github.com/aiming-lab/mdocagent
공식 코드MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
https://github.com/alibabaresearch/advancedliteratemachinery
공식 코드https://github.com/allenai/medicat
공식 코드MedICaT: A Dataset of Medical Images, Captions, and Textual References
https://github.com/amazon-science/visfocus
공식 코드VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding
https://github.com/andreagemelli/doc2graph
공식 코드Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
https://github.com/applicaai/ccpdf
공식 코드CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data
https://github.com/bobxwu/traco
공식 코드On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling
https://github.com/bunsenfeng/kalm
공식 코드https://github.com/chongzhangFDU/ROOR
공식 코드Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
https://github.com/christofid/DomainUnderstanding
공식 코드Understood in Translation, Transformers for Domain Understanding
https://github.com/clovaai/donut
공식 코드https://github.com/clovaai/webvicob
공식 코드On Web-based Visual Corpus Construction for Visual Document Understanding
https://github.com/copenlu/cite-worth
공식 코드CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding
https://github.com/danjacobellis/LCCL
공식 코드https://github.com/danjacobellis/walloc
공식 코드https://github.com/danyang-liu/KRED
공식 코드KRED: Knowledge-Aware Document Representation for News Recommendations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.