{"total":43,"rows":[{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107,"area":null},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"area":null},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64,"area":null},{"id":"2305.07498","title":"Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"area":null},{"id":"2105.11672","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2306.00526","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","created":"2023-06-01","cited_by_count":24,"area":null},{"id":"2106.10786","title":"ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction","created":"2021-06-21","cited_by_count":22,"area":null},{"id":"2106.12940","title":"MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction","created":"2021-06-24","cited_by_count":18,"area":null},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18,"area":null},{"id":"2104.08041","title":"Cost-effective End-to-end Information Extraction for Semi-structured Document Images","created":"2021-04-16","cited_by_count":14,"area":null},{"id":"2310.10760","title":"Towards reducing hallucination in extracting information from financial reports using Large Language Models","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2209.08569","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","created":"2022-09-18","cited_by_count":9,"area":null},{"id":"2308.13982","title":"Universal Graph Continual Learning","created":"2023-08-27","cited_by_count":9,"area":null},{"id":"2106.10681","title":"Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences","created":"2021-06-20","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2106.00978","title":"A Span Extraction Approach for Information Extraction on Visually-Rich Documents","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2401.02823","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2412.17092","title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2108.10395","title":"Using Neighborhood Context to Improve Information Extraction from Visual Documents Captured on Mobile Phones","created":"2021-08-23","cited_by_count":5,"area":null},{"id":"2104.04434","title":"Larger-Context Tagging: When and Why Does It Work?","created":"2021-04-09","cited_by_count":4,"area":null},{"id":"2306.17695","title":"A New Task and Dataset on Detecting Attacks on Human Rights Defenders","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2109.13967","title":"One-shot Key Information Extraction from Document with Deep Partial Graph Matching","created":"2021-09-26","cited_by_count":3,"area":null},{"id":"2204.07551","title":"Summarization with Graphical Elements","created":"2022-04-15","cited_by_count":2,"area":null},{"id":"2206.02628","title":"HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2303.02393","title":"Seq-HyGAN: Sequence Classification via Hypergraph Attention Network","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2410.01160","title":"GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2309.02902","title":"ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2409.13755","title":"Entity-Aware Self-Attention and Contextualized GCN for Enhanced Relation Extraction in Long Sentences","created":"2024-09-15","cited_by_count":1,"area":null},{"id":"2102.11047","title":"Semantic Parsing to Manipulate Relational Database For a Management System","created":"2021-02-18","cited_by_count":0,"area":null},{"id":"2106.00851","title":"Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations","created":"2021-06-01","cited_by_count":0,"area":null},{"id":"2106.00887","title":"Exploiting Global Contextual Information for Document-level Named Entity Recognition","created":"2021-06-02","cited_by_count":0,"area":null},{"id":"2108.11629","title":"Web Image Context Extraction with Graph Neural Networks and Sentence Embeddings on the DOM tree","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2111.15436","title":"KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers","created":"2021-11-30","cited_by_count":0,"area":null},{"id":"2305.14578","title":"Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2305.14590","title":"RE$^2$: Region-Aware Relation Extraction from Visually Rich Documents","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2305.15138","title":"Topic-Guided Self-Introduction Generation for Social Media Users","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2508.13404","title":"TASER: Table Agents for Schema-guided Extraction and Recommendation","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2603.00021","title":"From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization","created":"2026-02-03","cited_by_count":0,"area":null}],"next_cursor":null}