NLLP Workshop 2022 took place on 8 December 2022, co-located with the EMNLP 2022 conference.

The workshop proceedings are available here.

The recording of the workshop is available here.

[Michael Livermore] (https://www.law.virginia.edu/faculty/profile/mal5un/2457619) (University of Virginia School of Law) was the invited speaker.



All times are in GST time zone

09:00 - 10:40Session 1 (Chair: Ilias Chalkidis)
09:00 - 09:10Workshop opening
09:10 - 09:15Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities
Zejiang Shen (MIT); Kyle Lo (Allen Institute for Artificial Intelligence); Lauren Yu (University of Michigan); Nathan Dahlberg; Margo Schlanger (University of Michigan); Doug Downey (Allen Institute for AI, Northwestern University)
09:15 - 09:20Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance
Abhishek Agarwal; Shanshan Xu; Matthias Grabmair
09:20 - 09:25Towards Cross-Domain Transferability of Text Generation Models for Legal Text
Vinayshekhar Bannihatti Kumar (AWS AI); Kasturi Bhattacharjee (AWS AI, Amazon); Rashmi Gangadharaiah (AWS AI, Amazon)
09:25 - 09:35Joint Q&A
09:35 - 09:40Parameter-Efficient Legal Domain Adaptation
Jonathan Li (Queen's University); Rohan Bhambhoria (Queen's University); Xiaodan Zhu (Queen's University)
09:40 - 09:45ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US
Gil Semo (Darrow AI Ltd.); Dor Bernsohn (Darrow AI Ltd.); Ben Hagag (Darrow AI Ltd.); Gila Hayat (Darrow AI Ltd.); Joel Niklaus (University of Bern)
09:45 - 09:50Zero Shot Transfer of Legal Judgement Prediction as Article-aware Entailment for the European Court of Human Rights
T.Y.S.S Santosh (Technical University of Munich); Oana Ichim (Graduate Institute of International and Development Studies); Matthias Grabmair (Technical University of Munich)
09:50 - 09:55Revisiting Transformer-based Models for Long Document Classification
Xiang Dai; Ilias Chalkidis; Sune Darkner; Desmond Elliott
09:55 - 10:00Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers
Shanshan Xu (Technical University of Munich); Irina Broda (Technical University of Munich); Rashid Haddad (TUM); Marco Negrini (Technical University of Munich); Matthias Grabmair (Technical University of Munich)
10:00 - 10:05AraLegal-BERT: A pretrained language model for Arabic Legal text
Muhammad Al-Qurishi (King Saud University); Sarah AlQaseemi (Elm Company); Riad Souissi (Elm Company)
10:05 - 10:10An Efficient Active Learning Pipeline for Legal Text Classification
Sepideh Mamooler (Swiss Federal Institute of Technology Lausanne (EPFL)); Rmi Lebret (EPFL); Stephane Remo Massonnet (EPFL); Karl Aberer (EPFL)
10:10 - 10:15A Legal Approach to Hate Speech – Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task
Frederike Zufall (Max Planck Institute for Research on Collective Goods); Marius Hamacher (FernUniversitt in Hagen); Katharina Kloppenborg (Center for Research and Interdisciplinarity); Torsten Zesch (Computational Linguistics, FernUniversitt in Hagen)
10:15 - 10:20Validity Assessment of Legal Will Statements as Natural Language Inference
Alice Saebom Kwak (The University of Arizona); Jacob O. Israelsen (The University of Arizona); Clayton T. Morrison (The University of Arizona); Derek E. Bambauer (The University of Arizona); Mihai Surdeanu (The University of Arizona)
10:20 - 10:40Joint Q&A
10:40 - 11:00Break
11:00 - 12:40Session 2 (Chairs: Nikolaos Aletras & Leslie Barrett)
11:00 - 12:00Keynote Talk
Finding the Law - Mike Livermore (University of Virginia School of Law)
12:00 - 12:05Data-efficient end-to-end Information Extraction for Statistical Legal Analysis
Wonseok Hwang (LBox); Saehee Eom (LBox); Hanuhl Lee (LBox); Hai Jin Park (Hanyang Univ.); Minjoon Seo (KAIST)
12:05 - 12:10Efficient Deep Learning-based Sentence Boundary Detection in Legal Text
Reshma Sheik (National Institute of Technology, Trichy); Gokul Adethya T (National Institute of Technology, Trichy); S Jaya Nirmala (National Institute of Technology, Trichy)
12:10 - 12:15Semantic Segmentation of Legal Documents via Rhetorical Roles
Vijit Malik (Indian Institute of Technology Kanpur); Rishabh Sanjay (Indian Institute of Technology Kanpur); Shouvik Kumar Guha (Assistant Professor (Law), WBNUJS); Angshuman Hazarika (IIM Ranchi); Shubham Nigam (IIT Kanpur); Arnab Bhattacharya (Dept. of Computer Science and Engineering, IIT Kanpur); Ashutosh Modi (Indian Institute of Technology Kanpur)
12:15 - 12:20Detecting Relevant Differences Between Similar Legal Texts
Xiang Li (University of Ottawa); Jiaxun Gao (University of Ottawa); Diana Inkpen (University of Ottawa); Wolfgang Alschner (University of Ottawa)
12:20 - 12:25E-NER --- An Annotated Named Entity Recognition Corpus of Legal Text
Ting Wai Terence Au (University College London); Vasileios Lampos (University College London); Ingemar Cox (University College London, University of Copenhagen, Denmark)
12:25 - 12:40Joint Q&A
12:40 - 14:00Lunch & In-Person Poster Session (Lunch provided)
14:00 - 15:30Session 3 (Chair: Catalina Goanta)
14:00 - 14:05On What it Means to Pay Your Fair Share: Towards Automatically Mapping Different Conceptions of Tax Justice in Legal Research Literature
Reto Gubelmann (University of St.Gallen); Peter Hongler (University of St.Gallen); Elina Margadant (University of St.Gallen); Siegfried Handschuh (University of St. Gallen)
14:05 - 14:10Combining WordNet and Word Embeddings in Data Augmentation for Legal Texts
Sezen Perin (Boazii University); Andrea Galassi (University of Bologna); Francesca Lagioia (Cirsfid Alma-AI and Law department, University of Bologna, and Law Department, European University Institute); Federico Ruggeri (University of Bologna); Piera Santin (University of Bologna); Giovanni Sartor (University of Bologna); Paolo Torroni (Alma Mater - Universit di Bologna)
14:10 - 14:15Named Entity Recognition in Indian court judgments
Prathamesh Kalamkar (ThoughtWorks Technologies India Private Limited); Astha Agarwal (ThoughtWorks Technologies India Private Limited); Aman Tiwari (ThoughtWorks Technologies India Private Limited); Smita Gupta (Agami); Saurabh Karn (Agami); Vivek Raghavan (EkStep Foundation)
14:15 - 14:20Legal Named Entity Recognition with Multi-Task Domain Adaptation
Razvan-Alexandru Smadu (University Politehnica of Bucharest); Ion-Robert Dinica (University Politehnica of Bucharest); Andrei-Marius Avram (Research Institute for Artificial Intelligence, Romanian Academy); Dumitru-Clementin Cercel (University Politehnica of Bucharest); Florin Pop (University Politehnica of Bucharest); Mihaela-Claudia Cercel (First District Court of Giurgiu)
14:20 - 14:35Joint Q&A
14:35 - 14:40Do Charge Prediction Models Learn Legal Theory?
An Zhenwei; Quzhe Huang; Cong Jiang; Yansong Feng; Dongyan Zhao
14:40 - 14:45Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models
Stelios Maroudas (Cognitiv+, Athens University of Economics and Business); Sotiris Legkas (Cognitiv+, Athens University of Economics and Business); Prodromos Malakasiotis (Athens University of Economics and Business); Ilias Chalkidis (University of Copenhagen)
14:45 - 14:50Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer
Dimitris Mamakas (Athens University of Economics and Business); Petros Tsotsi (Athens University of Economics and Business); Ion Androutsopoulos (Athens University of Economics and Business); Ilias Chalkidis (University of Copenhagen)
14:50 - 14:55Privacy-Preserving Models for Legal Natural Language Processing
Ying Yin (Technische Universitat Darmstadt); Ivan Habernal (Technische Universitt Darmstadt)
14:55 - 15:00Automatic Classification of Legal Violations in Cookie Banner Texts
Marieke van Hofslot (Utrecht University); Almila Akdag Salah (Utrecht University); Albert Gatt (Utrecht University); Cristiana Santos (Utrecht Universiy)
15:00 - 15:05Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings
Daniel Braun (University of Twente)
15:05 - 15:30Joint Q&A
15:30 - 16:00Break
16:00 - 17:30Session 4 (Chair: Daniel Preotiuc-Pietro)
16:00 - 16:05Should I disclose my dataset? Caveats between reproducibility and individual data rights
Raysa M. Benatti (University of Campinas); Camila M. L. Villarroel (University of Sao Paulo); Sandra Avila (University of Campinas); Esther L. Colombini (University of Campinas); Fabiana C. Severi (University of Sao Paulo)
16:05 - 16:10Privacy Pitfalls of Online Service Terms and Conditions: a Hybrid Approach for Classification and Summarization
Emilia Lukose (University of Surrey); Suparna De (University of Surrey); Jon Johnson (University College London)
16:10 - 16:15Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions
Yang Zhong (University of Pittsburgh); Diane Litman (University of Pittsburgh)
16:15 - 16:20Abstractive Summarization of Dutch Court Verdicts Using Sequence-to-sequence Models
Marijn Schraagen (Utrecht University); Floris Bex (Utrecht University); Nick van de Luijtgaarden (Utrecht University); Daniel Prijs (Utrecht University)
16:20 - 16:25Graph-based Keyword Planning for Legal Clause Generation from Topics
Sagar Joshi (International Institute of Information Technology, Hyderabad); Sumanth Balaji (IIIT-Hyderabad, India); Aparna Garimella (Adobe Research); Vasudeva Varma (IIIT Hyderabad)
16:25 - 16:30Text Simplification for Legal Domain: Insights and Challenges
Aparna Garimella (Adobe Research); Abhilasha Sancheti (University of Maryland); Vinay Aggarwal (Adobe); Ananya Ganesh (University of Colorado Boulder); Niyati Chhaya (Adobe Research); Nandakishore Kambhatla (Adobe Research)
16:30 - 16:45Joint Q&A
16:45 - 16:50On Breadth Alone: Improving the Precision of Terminology Extraction Systems on Patent Corpora
Sean Nordquist (New York University); Adam Meyers (New York University)
16:50 - 16:55The Legal Argument Reasoning Task in Civil Procedure
Leonard Bongard (Technical University of Darmstadt); Lena Held (Technical University of Darmstadt); Ivan Habernal (Technische Universitt Darmstadt)
16:55 - 17:00Legal and Political Stance Detection of SCOTUS Language
Noah Bergam (Columbia University); Emily Allaway (Columbia University); Kathleen McKeown (Columbia University and Amazon (Amazon Scholar))
17:00 - 17:05Can AMR Assist Legal and Logical Reasoning?
Nikolaus Schrack (University of Copenhagen); Ruixiang Cui (University of Copenhagen); Hugo A. Lopez (Technical University of Denmark); Daniel Hershcovich (University of Copenhagen)
17:05 - 17:10LawngNLI: a long-premise benchmark for evaluating models on in-domain generalization to long contexts and implication-based retrieval
William Bruno; Dan Roth
17:10 - 17:15Legal Prompting: Teaching a Language Model to Think Like a Lawyer
Fangyi Yu (Thomson Reuters); Lee Quartey (Thomson Reuters); Frank Schilder (Thomson Reuters)
17:15 - 17:30Joint Q&A
17:30 - 18:30Panel Discussion (From NLLP to legal NLP: The Future of the Field) & Best Presentation Award


Organizing Committee

Programe Committee

Invited Speakers

Michael Livermore (University of Virginia School of Law)

Title: Finding the Law

Abstract: This presentation will examine challenges in “finding the law,” for both legal practitioners and scholars engaged in the computational analysis of law. For the practitioner, the challenge is one of search, a process that can be modeled and studied. Although undertheorized, law search has substantial jurisprudential and practical consequences that are only begining to be explored. For the computational scholar, challenges of selection and data bias are pervasive, and credible scholarship must ground descriptive and causal analyses in the actual processes that generate the data available for study.

Block Image

Bio: Michael A. Livermore is a Professor of Law at the University of Virginia. He is one of the early scholars involved in a new research paradigm in legal scholarship that uses computational text analysis tools to study the law and legal institutions. Livermore is the author of dozens of academic works, which have appeared in top law journals as well as peer-reviewed legal, scientific, and social science journals. With Daniel N. Rockmore, he edited Law as Data: Computation, Text, and the Future of Legal Analysis (Santa Fe Institute Press, 2019). Livermore hosts the Online Workshop on the Computational Analysis of Law, a global forum for scholars to present cutting-edge research in this area. Livermore is also a leading expert on the use of cost-benefit analysis to evaluate regulation. Prior to joining the faculty, Livermore was the founding executive director of the Institute for Policy Integrity at New York University School of Law, a think tank dedicated to improving the quality of government decision-making. He is a public member of the Administrative Conference of the United States.