# CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor

arXiv: https://arxiv.org/abs/1903.12363 · HTML: https://mlsanity.com/paper/1903.12363/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2019.

## Built on by (most cited first, 21 of 21)

- [StrucTexT: Structured Text Understanding with Multi-Modal Transformers](https://mlsanity.com/paper/2108.02923/) (2021)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [DocILE Benchmark for Document Information Localization and Extraction](https://mlsanity.com/paper/2302.05658/) (2023)
- [ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction](https://mlsanity.com/paper/2303.05063/) (2023)
- [ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents](https://mlsanity.com/paper/2105.11672/) (2021)
- [Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering](https://mlsanity.com/paper/2306.00526/) (2023)
- [ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction](https://mlsanity.com/paper/2106.10786/) (2021)
- [Deep Learning based Visually Rich Document Content Understanding: A Survey](https://mlsanity.com/paper/2408.01287/) (2024)
- [FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction](https://mlsanity.com/paper/2305.02549/) (2023)
- [DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/2304.12484/) (2023)
- [Cost-effective End-to-end Information Extraction for Semi-structured Document Images](https://mlsanity.com/paper/2104.08041/) (2021)
- [Business Document Information Extraction: Towards Practical Benchmarks](https://mlsanity.com/paper/2206.11229/) (2022)
- [ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding](https://mlsanity.com/paper/2209.08569/) (2022)
- [Key Information Extraction From Documents: Evaluation And Generator](https://mlsanity.com/paper/2106.14624/) (2021)
- [QueryForm: A Simple Zero-shot Form Entity Query Framework](https://mlsanity.com/paper/2211.07730/) (2022)
- [TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/2207.06744/) (2022)
- [Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features](https://mlsanity.com/paper/2208.04011/) (2022)
- [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025)
- [DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction](https://mlsanity.com/paper/2103.05908/) (2021)
- [DocILE 2023 Teaser: Document Information Localization and Extraction](https://mlsanity.com/paper/2301.12394/) (2023)
- [End-to-End Document Classification and Key Information Extraction using Assignment Optimization](https://mlsanity.com/paper/2306.00750/) (2023)

## Abstract (arXiv)

Extracting key information from documents, such as receipts or invoices, and preserving the interested texts to structured data is crucial in the document-intensive streamline processes of office automation in areas that includes but not limited to accounting, financial, and taxation areas. To avoid designing expert rules for each specific type of document, some published works attempt to tackle the problem by learning a model to explore the semantic context in text sequences based on the Named Entity Recognition (NER) method in the NLP field. In this paper, we propose to harness the effective information from both semantic meaning and spatial distribution of texts in documents. Specifically, our proposed model, Convolutional Universal Text Information Extractor (CUTIE), applies convolutional neural networks on gridded texts where texts are embedded as features with semantical connotations. We further explore the effect of employing different structures of convolutional neural network and propose a fast and portable structure. We demonstrate the effectiveness of the proposed method on a dataset with up to 4,484 labelled receipts, without any pre-training or post-processing, achieving state of the art performance that is much better than the NER based methods in terms of either speed and accuracy. Experimental results also demonstrate that the proposed CUTIE model being able to achieve good performance with a much smaller amount of training data.