Legal teams are more overloaded than ever: suffering from slow processes and inefficiencies, they spend a vast amount of time working on tedious low-level tasks that can be automated with DeepJudge.
We have conducted dozens of interviews with legal experts and are in close contact with several lead- ing law firms in Switzerland and Germany, who have provided us with deep insights into their work routine. The emerging picture is clear: the manual processing of large document collections is one of the biggest culprits in the workflow of lawyers.
Founded by four ETH Machine Learning PhDs, with over 20+ years of combined experience with Deep Learning and Natural Language Processing at scale, DeepJudge sets a new bar in context-aware legal document understanding. We develop a context-aware legal document processing AI. At the core of our technology is an AI that understands natural language and is trained on millions of documents. The result- ing quality and efficiency gains provide a real competitive advantage to our customers, freeing-up lawyers to focus on the truly strategic aspects of their work.
DeepJudge is an ETH spin-o supported by the ETH AI Center focusing on legal tech. Based on our own research and know-how we developed an AI that is context-aware (i.e. understands the semantics of legal documents and unstructured text) and can be used as an assistant to lawyers for various manual repetitive tasks (e.g. document redaction or document search) in order to boost performance. Our technology is currently available only in German. It is of crucial importance to us to extend our technology to a multilingual document understanding AI that can reason and process documents in various languages to be able to expand internationally. The ﬁrst goal of our project is to collect and preprocess data in di erent languages (concretely English, French and Italian) before starting to train the AI.
Persons involved in the project
Last update to this project presentation 29.07.2021