Natural Language Processing and AI will likely transform the work of legal professionals. While there already exists lots of commercial legal AI tech, we zoom in on the potential of such technology for public agencies. Specifically, we collaborate with public legal services and investigate how AI can assist such services. We do not want to develop tools which eventually would automate away manual labor but want to build legal tech which assists them in their everyday work.

This talk presents work in progress. Preliminary findings of an early prototype which retrieves relevant information and legal arguments for search queries will be presented. We'll dive into technical details of that system, its current limitations and future work. Lastly, we'll elaborate on how public agencies have different requirements than private law firms, and how current legal tech does not cater towards the exact needs of such public agencies. 

Bio:

Dominik Stammbach’s research explores applications and the new development of Natural Language Processing methods. He is especially interested in NLP for enhancing access to justice, making law accessible, developing methods to detect misinformation (around climate change and climate change denial) and corporate greenwashing. Stammbach’s work combines a focus on high-quality data and recent trends in NLP. In his dissertation, Stammbach was developing methods towards data-centric automated fact checking, where he investigated how to extract relevant evidence from long documents, and explored the roles of different knowledge bases in automated fact checking. He was also involved in various projects around enhancing access to justice and making law accessible, and using NLP methods to provide accurate and faithful information around climate change, and to automatically detect misinformation around climate change. His research was published at conferences such as The Annual Meeting of the Association for Computational Linguistics (ACL) and The Conference on Empirical Methods in Natural Language Processing (EMNLP), and various journals such as Communications Earth & Environment, Cognition, and the ACM Journal of Data and Information Quality. Stammbach completed his Ph.D. at ETH Zurich (Switzerland), and earned a master’s degree in language science and technology from Saarland University (Germany).

In-person attendance is open to Princeton University faculty, staff and students. This talk will be open to the public via Zoom. It will be recorded and posted here, on the CITP YouTube channel, and on the Princeton University Media Central channel.

If you need an accommodation for a disability please contact Jean Butcher at [email protected] at least one week before the event.

Sponsorship of an event does not constitute institutional endorsement of external speakers or views presented.