Graph Convolution for Multimodal Information Extraction from Visually Rich Documents

Visually rich documents (VRDs) are ubiquitous in daily business and life. Examples are purchase receipts, insurance policy documents, custom declaration forms and so on. In VRDs, visual and layout information is critical for document understanding, and texts in such documents cannot be serialized into the one-dimensional sequence without losing information. Classic information extraction models such as BiLSTM-CRF typically operate on text sequences and do not incorporate visual features. In this paper, we introduce a graph convolution based model to combine textual and visual information presented in VRDs. Graph embeddings are trained to summarize the context of a text segment in the document, and further combined with text embeddings for entity extraction. Extensive experiments have been conducted to show that our method outperforms BiLSTM-CRF baselines by significant margins, on two real-world datasets. Additionally, ablation studies are also performed to evaluate the effectiveness of each component of our model.

[1]  Eric Nichols,et al.  Named Entity Recognition with Bidirectional LSTM-CNNs , 2015, TACL.

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

[3]  Roberto Cipolla,et al.  Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[5]  Yansong Feng,et al.  Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks , 2018, ArXiv.

[6]  Eric Medvet,et al.  A probabilistic approach to printed document understanding , 2011, International Journal on Document Analysis and Recognition (IJDAR).

[7]  Yue Zhang,et al.  N-ary Relation Extraction using Graph-State LSTM , 2018, EMNLP.

[8]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[9]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[10]  Yue Zhang,et al.  Joint Extraction of Entities and Relations Based on a Novel Graph Scheme , 2018, IJCAI.

[11]  Alexander M. Rush,et al.  Character-Aware Neural Language Models , 2015, AAAI.

[12]  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).

[13]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[14]  Steffen Bickel,et al.  Chargrid: Towards Understanding 2D Documents , 2018, EMNLP.

[15]  Li Fei-Fei,et al.  Image Generation from Scene Graphs , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[18]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[19]  Eduard H. Hovy,et al.  End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF , 2016, ACL.

[20]  Vincent Poulain D'Andecy,et al.  Field Extraction from Administrative Documents by Incremental Structural Templates , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[21]  Vincent Poulain D'Andecy,et al.  Field Extraction by Hybrid Incremental and A-Priori Structural Templates , 2018, 2018 13th IAPR International Workshop on Document Analysis Systems (DAS).

[22]  Erik F. Tjong Kim Sang,et al.  Representing Text Chunks , 1999, EACL.

[23]  Frederick Reiss,et al.  Rule-Based Information Extraction is Dead! Long Live Rule-Based Information Extraction Systems! , 2013, EMNLP.

[24]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

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

[26]  Nanyun Peng,et al.  Cross-Sentence N-ary Relation Extraction with Graph LSTMs , 2017, TACL.