Esker Presenting Data Extraction Technology at ICDAR, World’s Top AI Conference
LYON, France, and MIDDLETON, Wis. — Sept. 23, 2019 — Esker, a worldwide leader in AI-driven process automation solutions and pioneer in cloud computing, today announced that it is presenting the results of its research on data extraction at the 2019 International Conference on Document Analysis and Recognition (ICDAR), the world’s top AI conference, in Sydney Australia. Also known as the “World Cup” in the field of document analysis and recognition, ICDAR is the biggest international gathering for researchers, scientists and practitioners in the document analysis community.
Clément Sage, a machine-learning PhD student and engineer at Esker, will present his paper titled “Recurrent Neural Network Approach for Table Field Extraction in Business Documents” in the context of his PhD research at Université Claude Bernard Lyon 1 in France.
Efficiently extracting information from incoming business documents, such as orders and invoices, is crucial for companies that face massive daily document flows. These documents contain valuable information that companies need to retrieve for integration in their ERP system and structured archiving. However, automating data extraction is extremely challenging, especially when analyzing table content to identify ordered or invoiced items, as the documents have complex and ambiguous structures.
To address this problem, Esker developed an end-to-end method for table fields’ extraction by bypassing physical structure recognition. Esker proposes a generic approach based on deep learning, which enables order item identification on layouts not necessarily seen during training. Sage’s first-time recognition approach is of particular interest to researchers, as it is generic enough to easily be adapted for other document types and relies on little domain specific textual preprocessing. This universal and nonproprietary AI algorithm is an important discovery for the document community.
Esker successfully evaluated the effectiveness of this approach on real-world purchase orders to retrieve product numbers, quantities and unit prices from ordered items. Following positive results, Esker is now using this technology on its cloud-based platform. The company’s customers are already benefiting from improved data recognition on new documents and better automation rates.
“AI technologies are imperative for businesses that want to maintain a competitive edge,” said Jean-Jacques Bérard, Executive Vice President, Research & Development at Esker. “By enabling businesses to recognize table fields on first-time orders, Esker helps increase productivity and operational efficiencies. What’s particularly exciting is that the best AI approaches for natural language processing apply extraordinarily well to the field of business documents and constitute a huge reservoir of innovations for the future.”
“This technology demonstrates how exceptionally efficient AI can be,” said Clément Sage, PhD student and engineer at Esker. “We are currently working on next generation AI services and I'm confident that we will soon be able to tackle the challenge of extracting entirely clean and reliable data from orders and invoices in a first instance and other business documents soon after.”
Clément Sage, along with his two co-authors, Jérémy Espinas, PhD supervisor at Esker, and Véronique Eglin, PhD supervisor at LIRIS laboratory and professor at INSA Lyon, will present on September 25, 2019, from 3:20 – 5:00 p.m. in the Cockle Bay room at the Sydney Convention and Exhibition Centre.
Esker is a worldwide leader in cloud-based document process automation software, helping financial and customer service departments digitally transform their purchase-to-pay (P2P) and order-to-cash (O2C) cycles. Used by more than 6,000 companies worldwide, Esker’s solutions incorporate technologies like artificial intelligence (AI) to drive increased productivity, enhanced visibility, reduced fraud risk, and improved collaboration with customers, suppliers and internally. Esker operates in North America, Latin America, Europe and Asia Pacific with global headquarters in Lyon, France, and U.S. headquarters in Madison, Wisconsin. For more information on Esker and its solutions, visit www.esker.com. Follow Esker on Twitter @EskerInc and join the conversation on the Esker blog at blog.esker.com.