CloudScan - A configuration-free invoice analysis system using recurrent neural networks
Authors:
Preprint
Abstract
We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation. In contrast to previous work, CloudScan does not rely on templates of invoice layout, instead it learns a single global model of invoices that naturally generalizes to unseen invoice layouts. The model is trained using data automatically extracted from end-user provided feedback. This automatic training data extraction removes the requirement for users to annotate the data precisely. We describe a recurrent neural network model that can capture long range context and compare it to a baseline logistic regression model corresponding to the current CloudScan production system. We train and evaluate the system on 8 important fields using a dataset of 326,471 invoices. The recurrent neural network and baseline model achieve 0.891 and 0.887 average F1 scores respectively on seen invoice layouts. For the harder task of unseen invoice layouts, the recurrent neural network model outperforms the baseline with 0.840 average F1 compared to 0.788.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Neural Machine Translation of Rare Words with Subword Units2016
- Neural Architectures for Named Entity Recognition2016
- Lasagne: First Release.2015
- Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding2013
- A probabilistic approach to printed document understandingInternational Journal on Document Analysis and Recognition (IJDAR), 2010
- Feature hashing for large scale multitask learning2009
- Analysis and understanding of multi-class invoicesInternational Journal on Document Analysis and Recognition (IJDAR), 2003
- The Myth of the Paperless Office2001
- Long Short-Term MemoryNeural Computation, 1997
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955