Teklia has developed for its clients automatic document understanding systems based on Machine Learning in a wide range of application domains.

Genealogical information extraction

Names, places, roles and relation extraction in 1.8 million parish records from Quebec between 1880 and 1920.

handwriting recognition named-entities extraction.

Automatic information redaction

Redaction of confidential information in fiscal forms. Automatic processing of a 2.5 million documents archive.

document clustering document image classification

Semantic Analysis of Mails

Automatic prediction of priority levels from complaint mails.

OCR topic detection document classification

Analysis of Local Town Planning

Automatic extraction of construction rules from Local Town Planning (Plan locaux d'urbanisme).

term extraction word embeddings visualisation

Information extraction from medical record

Classification and numerical information extraction from medical records

document classification named-entities extraction

Information extraction from scanned invoices

Automatic extraction financial information in scanned invoices

numerical entities extraction deep learning confidence measures

Case Law Decisions Understanding

Data extraction, classification and summarization of case law decisions.

Internal Control Procedures Analysis

Normalization and organization of internal control definitions.

text distance concept extraction word embeddings

Automatic IT Tickets Processing

Clustering of tickets by topics, automatic tickets classification and triaging.

density-based spatial clustering keyword extraction classification