Mining and Learning in the Legal Domain
International Workshop on Mining and Learning in the Legal Domain (MLLD-2021)
In conjunction with the 21st IEEE International Conference on Data Mining, December 7-10, 2021, Auckland, New Zealand
The increasing accessibility of large legal corpora and databases create opportunities to develop data driven techniques as well as more advanced tools that can facilitate multiple tasks of researchers and practitioners in the legal domain. While recent advancements in the areas of data mining and machine learning have gained many applications in domains such as biomedical, healthcare and finance, there is still a noticeable gap in how much the state-of-the-art techniques are being incorporated in the legal domain. Achieving this goal entails building a multi-disciplinary community that can benefit from the competencies of both law and computer science experts. The goal of this workshop is to bring the researchers and practitioners of both disciplines together and provide an opportunity to share the latest novel research findings and innovative approaches in employing data analytics and machine learning in the legal domain.
Following the success of the 1st MLLD workshop (MLLD 2020), the 2nd workshop on Mining and Learning in the Legal Domain (MLLD 2021) discusses a broad variety of topics in various aspects of analyzing legal data such as Legislations, litigations, court cases, contracts, patents, Non-Disclosure Agreements (NDAs) and Bylaws. We encourage submissions on novel mining and learning based solutions in:
Applications of data mining techniques in the legal domain
case outcome prediction
classifying, clustering and identifying anomalies in big corpora of legal records
citation analysis for case law
Applications of natural language processing and machine learning techniques for legal textual data
information extraction and entity extraction/resolution for legal document reviews
information retrieval and question answering in applications such as identifying relevant case law
summarization of legal documents
legal language modelling and legal document embedding and representation
recommender systems for legal applications
topic modelling in large amounts of legal documents
harnessing of deep learning approaches
Ethical issues in mining legal data
privacy and GDPR in legal analytics
bias in the applications of data mining
transparency in legal data mining
Training data for legal domain
acquisition, representation, indexing, storage, and management of legal data
automatic annotation and learning with human in the loop
data augmentation techniques for legal data
semi-supervised learning, domain adaptation, distant supervision and transfer learning
Emerging topics in the intersection of data mining and law
digital lawyers and legal machines
future of law practice in the age of AI
You are invited to submit your original research and application papers to the workshop. As per ICDM instructions, papers are limited to a maximum of 8 pages, and must follow the IEEE ICDM format requirements. All accepted workshop papers will be published in the formal proceedings by the IEEE Computer Society Press. Each paper is reviewed by at least 3 reviewers from the program committee. Paper review is triple-blind. Manuscripts are to be submitted through CyberChair. Please forward your questions to the organizing committee.
Thomson Reuters Labs Best Paper Award
Thomson Reuters Labs will generously provide a total of $1000 USD to the best paper(s) submitted (one $1000 award or two $500 awards). The successful paper(s) must have at least one student author, and a student must be cited as the first author. The best paper recipient(s) will be selected by the program committee.
Thomson Reuters Labs is hiring! TR Labs is looking for experienced candidates across research, data science, engineering and more, in Toronto, Bangalore, Zurich, London, and Minneapolis St. Paul. Learn more about these opportunities here.
Paper submission due date: September 6 , 2021 Notification of acceptance: September 24, 2021 Camera ready submission: October 1, 2021
MLLD Panel on "The Future of AI and Law": November 22, 2021 at 9-10:15am Eastern Standard Time (EST)
MLLD -2021 Workshop: December 6, 2021 at 8-11:30pm Eastern Standard Time (EST)
December 7, 2021 at 2-5:30pm New Zealand Standard Time (NZST)
Wolfgang Alschner, University of Ottawa, Canada
Kevin Ashley, University of Pittsburgh, USA
Karl Branting, MITRE Corporation, USA
Jack Conrad, Thomson Reuters Labs, USA
Anna Farzindar, University of Southern California, USA
Randy Goebel, University of Alberta, Canada
Diana Inkpen, University of Ottawa, Canada
Daniel Martin Katz, Illinois Tech - Chicago Kent College of Law, USA
Sourav Mukherjee, Fairleigh Dickinson University, Canada
Isabelle Moulinier, Thomson Reuters Labs, USA
Aileen Nielsen, ETH Zurich, Switzerland
Adam Roegiest, Kira Systems, Canada
Ken Satoh, National Institute of Informatics, Japan
Jaromír Šavelka, University of Pittsburgh, USA
Frank Schilder, Thomson Reuters Labs, USA
Vasilis Tsolis, Cognitiv+, UK
Hannes Westermann, Université de Montréal
Adam Wyner, Swansea University, UK
Farhana Zulkernine, Queens University, Canada
"Detection of Similar Legal Cases on Personal Injury", Jason Lam, Yuhao Chen, Farhana Zulkernine, and Samuel Dahan [Best Paper Award Winner]
"Simplify Your Law: Using Information Theory to Deduplicate Legal Documents", Corinna Coupette, Jyotsna Singh, and Holger Spamann
"Legal Entity Extraction using a Pointer Generator Network", Stavroula Skylaki, Ali Oskooei, Omar Bari, Nadja Herger, and Zac Kriegman
"Determining Standard Occupational Classification Codes from Job Descriptions in Immigration Petitions", Sourav Mukherjee, David Widmark, Vince DiMascio, and Tim Oates
The workshop will be held on Dec 6th at 8-11:30 pm Eastern Time. The session is open to the public through
Meeting ID: 975 7275 6906
It is with great honor to announce that Prof. Sharad Goel of Harvard University will be giving the keynote talk at 2nd MLLD workshop.
Sharad Goel is a Professor of Public Policy at the Harvard Kennedy School. He looks at public policy through the lens of computer science, bringing a computational perspective to a diverse range of contemporary social and political issues, including criminal justice reform, democratic governance, and the equitable design of algorithms. Prior to joining Harvard, Sharad was on the faculty at Stanford University, with appointments in Management Science & Engineering, Computer Science, Sociology, and the Law School. He holds a BS in mathematics from the University of Chicago, as well as an MS in Computer Science and a PhD in Applied Mathematics from Cornell University.
Title: Designing Equitable Algorithms for Criminal Justice and Beyond
Abstract: Machine learning methods are increasingly used to model risk in criminal justice, banking, healthcare, and other high-stakes domains. These new tools promise gains in accuracy, but also raise challenging statistical, legal, and ethical questions. In this talk, I’ll describe the dominant axiomatic approach to fairness in machine learning, and argue that common mathematical definitions of fairness can, perversely, lead to discriminatory outcomes in practice. I’ll then present an alternative, consequentialist perspective for designing equitable algorithms that foregrounds the inherent tension between competing concerns in many real-world problems.
MLLD will host a panel on The Future of AI and Law with a lineup of experienced industry practitioners, governments personnel, and academics. The panelists will discuss topics such as emerging use cases of AI in law, issues relevant to adoption of AI, responsible AI, etc. Here is the full list of our panelists.
Ann Cavoukian, Ph.D., LL.D. (Hon), M.S.M
Executive Director at Global Privacy & Security by Design Centre
Data and Time
The panel session will be held on Nov 22nd at 9-10:15 am Eastern Time and is open to the public via this link. The passcode for the meeting is 2021. A recorded version of the panel session will be shared with ICDM attendees.
A recorded version of the panel session is available here.
Access of AI capabilities in justice system
Ethics, bias, and fairness
Interpretability and explainability, and the trade-off between explainability and IP rights. Can we have both?
Privacy and GDPR
Emerging use cases: What are the most probable use cases of AI/ML in law over the next decade? Examples:
Legal language simplification: Creating AI models (e.g., GPT-3 to simplify the legal language for users)
Meaningful summarization of legal text
The role of data scientists in contract life-cycle management
Human in the loop: How will humans be involved in the future AI-enabled decision makers? Will future AI solutions be fully automated with zero human supervision, or will humans have the final say in a decision assisted by AI?
After proper human evaluations, AI systems can make decisions without human interaction/supervision,
Humans review AI decisions and accept or reject them,
Humans will be the primary decision makers, but they will utilize the AI systems for assistance (AI-augmented decision making),
Adoption of AI: What will convince/force law firms to adopt AI in their practice? What are the incentives and deterrents?
The promise of AI: Is AI a hype or are AI-enabled solutions performing as promised?
Where have we seen success of AI in LegalTech
What will it take lawyers to adopt AI? How can we gain their trust?
AI cost savings opportunities vs cost of adoption of AI,
Regulating body: Who should be the decision makers as to what AI-enabled solutions would be allowed to make decisions that impact people?
Governments: may be slow and have historically shown lack of expertise,
Big tech: no incentive,
A new advisory/consultancy board comprised of academics, government, and big tech
Masoud Makrehchi, OntarioTech University and Thomson Reuters Labs
Shohreh Shaghaghian, Thomson Reuters Labs
Ali Vahdat, Thomson Reuters Labs
Fattane Zarrinkalam, Thomson Reuters Labs