Welcome to the second edition of the NLLP (Natural Legal Language Processing) Workshop, co-located with KDD 2020. Due to the Covid-19 pandemic, this year the workshop is held on-line as a live webinar.
Many industries have embraced approaches based on Data Science (DS), Natural Language Processing (NLP), Machine Learning (ML) and, more generally, Artificial Intelligence (AI), which have altered healthcare, finance, education and other fields. The legal domain, however, remains largely underrepresented in this literature, despite its enormous potential for generating interesting research problems. Electronic tools are increasingly used for all types of legal tasks and that use is predicted to grow sharply. By its very nature, the practice of law necessarily involves the analysis and interpretation of language and data. The potential for DS, AI, NLP or ML to provide benefit to practitioners of law and consumers of legal services around the world is, therefore, enormous.
We organized this workshop to bring together researchers and practitioners from around the world who develop DS, AI, NLP or ML techniques and applications for legal documents and, more generally, legal data. This is an exciting opportunity to expand the boundaries of our field by identifying new problems and exploring new data as it interacts with the full inventory of AI approaches. In this spirit, the Organizing and Program Committee was assembled to include researchers from both academia and industry, and from both computational and legal backgrounds.
We solicited five types of papers: (1) applications of DS, AI, NLP or ML methods to legal tasks; (2) experimental results using and adapting DS, AI, NLP or ML methods for legal data; (3) descriptions of new legal tasks for DS, AI, NLP or ML; (4) creation of curated and/or annotated resources; (5) descriptions of systems that use DS, AI, NLP or ML technologies for legal documents. We also ofered the option of submitting original unpublished research as non-archival in order to accommodate publication of the work at a later date in a conference or journal. Non-archival submissions were reviewed following the same procedure as for archival submissions.
We received 22 submissions and accepted 12 papers for an overall acceptance rate of 54.5%, all with oral presentation slots. Out of the 12 accepted papers, 6 are long papers, 4 are short papers and 2 are original work submitted as non-archival. Each paper was reviewed by at least 3 members of the Program Committee. The papers cover a range of topics including quantitative analyses of legal documents and research, new data sets and predictive methods, building NLP tools to process legal documents, and system descriptions for processing legal text.
We thank our invited speaker, Paul Nemitz, for accepting our invitation. Paul Nemitz is the Principal Advisor in the Directorate General for Justice and Consumers at the European Commission and has led the reform of Data Protection legislation in the EU. He will present a talk titled: "AI for language, democracy and fundamental rights". We hope his talk will ofer a fresh perspective for the attendees and will inspire new applications in this area.
We also thank everyone who expressed interest in the workshop, all authors of submitted papers, members of the Program Committee who did an excellent job at reviewing papers given a short turnaround time, everyone attending the workshop, KDD 2020 for hosting us and the workshop and publication chairs for their support. We especially thank our sponsors – Bloomberg and Bloomberg Law – for their support.
We are looking forward to meeting the authors and the other participants on-line.
Seth Kulick, University of Pennsylvania (US) Vasileios Lampos, University College London (UK) Junyi Jessy Li, University of Texas at Austin (US) How Khang Lim, Singapore Management University (Singapore) Prodromos Malakasiotis, Athens University of Economics and Business, and NCSR ‘Demokritos’ (Greece) Jelena Mitrovic, University of Passau (Germany) Hamid Motahari, Ernst & Young (UK) Georg Rehm, DFKI (Germany) Victor Rodríguez-Doncel, Universidad Politécnica de Madrid (Spain) Victoria Rubin, University of Western Ontario (Canada) George Sanchez, Thomson Reuters (US) Dan Simonson, Blackboiler (US) Jerrold Soh, Singapore Management University (Singapore) Gerasimos Spanakis, Maastricht University (Netherlands) Amanda Stent, Bloomberg LP (US) Maosong Sun, Tsinghua University (China) Dimitrios Tsarapatsanis, University of York (UK) Jianqian Wang, SUNY Bufalo (US) Adam Wyner, Swansea University (UK) Marcos Zampieri, Rochester Institute of Technology (US) Lina Zhou, University of Maryland, Baltimore County (US)