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