TABSTRACT Table Extraction Service From Unstructured Documents
Share this Session:
  George Roth   George Roth
President and CEO
Recognos Inc.


Tuesday, January 31, 2017
05:00 PM - 05:45 PM

Level:  Technical - Intermediate

The detection of table lines in an unstructured document has two major components. First, during a feature extraction phase, text lines are described by a set of features (derived from the table model), and then a deep neural network classifier is trained to distinguish between table and non-table lines. Training of a classifier is justified by the large diversity of table structures which make very difficult to define clear cuts and conditions to separate tables from non-tables, especially when a large number of descriptors are used to characterize a text line.

The TABSTRACT SaaS is used to extract the tables from an unstructured document and store the results in a spreadsheet. The extractors can be also accessed via an API. The extractor is integrated with the Recognos ETI Data Extraction Platform.

George Roth was born in Cluj, one of Romania's most important cities. He graduated with an MS in Mathematics and Computer Science from the “Babes Bolyai" University in Cluj in 1980. His career started at the Cluj Territorial Center for Computation (CTCE) where he worked until 1991, when he emigrated to the U.S. During his early years in the U.S., he worked as a Software Architect on numerous projects for large financial institutions in the US and Europe. George was the Lead Architect of SUMS (Security Universe Management System), a comprehensive financial data cleansing tool implemented at very large financial institutions in the US and Europe. In 1999, together with Ken Rogers, he started Recognos Inc. One year later, George, Kendal Rogers, and a Romanian partner established Recognos Romania, Inc., a U.S. – Romanian joint venture in Cluj, Romania. He is one of the founding members of the Romanian American Business Network, whose mission it is to bring together people with an interest in Romanian and US business cooperation. George Roth currently lives in Los Gatos, CA.

Close Window