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

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.

[1]  Bertin Klein,et al.  smartFIX: A Requirements-Driven System for Document Analysis and Understanding , 2002, Document Analysis Systems.

[2]  Dong Liu,et al.  Deep High-Resolution Representation Learning for Human Pose Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Alexander Schill,et al.  Automatic indexing of scanned documents: a layout-based approach , 2012, Electronic Imaging.

[5]  Alexander Schill,et al.  Intellix -- End-User Trained Information Extraction for Document Archiving , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[6]  Ole Winther,et al.  CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[7]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[8]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[9]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[10]  Iasonas Kokkinos,et al.  Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs , 2014, ICLR.