mlsanityData to 14 Oct 2026

Cost-effective End-to-end Information Extraction for Semi-structured Document Images

arXiv 2104.08041 ↗First posted 16 Apr 2021cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider an end-to-end model that directly maps the input to the target output and simplify the entire process. However, such generation approach is known to lead to unstable performance if not designed carefully. Here we present our recent effort on transitioning from our existing pipeline-based IE system to an end-to-end system focusing on practical challenges that are associated with replacing and deploying the system in real, large-scale production. By carefully formulating document IE as a sequence generation task, we show that a single end-to-end IE system can be built and still achieve competent performance.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 16 Apr 2021.

Builds on

19 of 22 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  5. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  6. 2019Image-based table recognition: data, model, and evaluationcited by 237
  7. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 218
  8. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  9. 2016Recurrent Neural Network Grammarscited by 109
  10. 2018Chargrid: Towards Understanding 2D Documentscited by 100
  11. 2018TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generationcited by 88
  12. 2019Graph Convolution for Multimodal Information Extraction from Visually Rich Documentscited by 88
7 more
  1. 2020PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networkscited by 72
  2. 2020Spatial Dependency Parsing for Semi-Structured Document Information Extractioncited by 65
  3. 2019BERTgrid: Contextualized Embedding for 2D Document Representation and Understandingcited by 63
  4. 2018GraphIE: A Graph-Based Framework for Information Extractioncited by 45
  5. 2020Transition-based Parsing with Stack-Transformerscited by 38
  6. 2017CloudScan - A configuration-free invoice analysis system using recurrent neural networkscited by 33
  7. 2019CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractorcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 2; 2024: 4; 2025: 1; 2026: 1.

14 papers.

Sort:

By area:

  1. 2021OCR-free Document Understanding Transformercited by 407
  2. 2022End-to-end Document Recognition and Understanding with Dessurtcited by 73
  3. 2022A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Predictioncited by 44
  4. 2024VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understandingcited by 8
  5. 2024ReALM: Reference Resolution As Language Modelingcited by 7
  6. 2022On Web-based Visual Corpus Construction for Visual Document Understandingcited by 5
  7. 2022Data-efficient End-to-end Information Extraction for Statistical Legal Analysiscited by 3
  8. 2024TreeForm: End-to-end Annotation and Evaluation for Form Document Parsingcited by 3
  9. 2023Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understandingcited by 2
  10. 2026Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesiscited by 1
  11. 2022Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matchingcited by 0
  12. 2023DUBLIN -- Document Understanding By Language-Image Networkcited by 0
2 more
  1. 2024Noise-Aware Training of Layout-Aware Language Modelscited by 0
  2. 2025Neurosymbolic Information Extraction from Transactional Documentscited by 0