Language understanding is a cognitive task at the highest level and a major discipline of artificial intelligence. Natural Language Processing (NLP) enables us to interpret written as well as spoken language and to extract and learn contextual information relevant for our application domains.

AIT provides the expertise and support for a broad range of use cases with regard to large text corpora. We apply a variety of machine-learning techniques – including algorithmics, mathematics and statistics as well as deep-learning techniques – to discover topics and semantic relationships, and to extract meaningful, structured information.

One essential aspect of NLP tasks is to minimize the effort required for the costly annotation and labelling of text, because this task relies on manual work and domain knowledge.  AIT’s open source annotation platform Recogito provides a flexible, efficient, and highly customizable environment for rapid annotation, and can make use of existing tag vocabularies and authority files to aid in the process of producing the high-quality ground-truth training data required for supervised machine-learning tasks.