See below for workshop program schedule; Papers available to participants here
The Second Workshop on Automated Detection, Extraction and Analysis of Semantic Information in Legal Texts (ASAIL) will be held in conjunction with ICAIL 2017: XVI International Conference on AI and Law, Friday June 16th 2017, London, UK. It is a continuation of the successful 2015 ASAIL workshop.
This workshop will bring together an interdisciplinary group of scholars, academic and corporate researchers, legal practitioners, and legal service providers for an extended, collaborative discussion about applying natural language processing and machine learning to the semantic analysis of legal texts. Semantic analysis is the process of relating syntactic elements and structures, drawn from the levels of phrases, clauses, sentences, paragraphs, and whole documents, to their language-independent meanings in a given domain, including meanings specific to legal information. The range of focal texts includes:
- statutes, regulations, and court-made pronouncements of legal rules embodying legal norms,
- textual arguments in legal case opinions interpreting legal norms and applying them in concrete fact situations,
- legislative and policy-based debates concerning proposed legal norms, their purpose and meaning,
- actual and proposed contracts that need to be analyzed for the permissions and obligations they encode and their consistency with organizational preferences or legal frameworks.
Researchers have long been developing tools to aggregate, synthesize, structure, summarize, and reason about legal norms and arguments in texts. Recently, however, dramatic advances in natural language processing, text and argument mining, information extraction, and automated question answering are changing how automatic semantic analysis of legal rules and arguments will be performed in the future. The discussion will include, but will not be limited to, retrieving documents with varying concepts of relevance, extracting legal norms from retrieved documents, and extracting various sorts of arguments. A priority will be given to topics that discuss both natural language texts and methods of representation or analysis.
Covered Topics
- Application of NLP to analyze arguments in legal texts: identification, annotation, and extraction of argument elements; relating arguments; and classifying arguments
- Automated or semi-automated approaches to extracting legal norms from legal texts
- Creation/evaluation of high quality annotated natural language legal corpora
- Automated semantic analysis of legal texts
- Development of computer-supported annotation environments for automated semantic analysis of legal texts
- Applications of machine learning to train automatic systems on tasks related to semantic analysis of legal texts, identifying legal norms, or extracting legal argumentation
- Summarization, visualization, and information retrieval for legal texts
- Argument mining of court cases, legislative records, legal policy debates and other legal documents
- Automated translations of legal text to formal or abstract representations that can be used for reasoning
- Applications of computational models of legal argumentation to guide interpretation of legal texts
- Application of linguistic theories of syntax, semantics, pragmatics, and discourse to legal texts
- Adaptation of NLP tools to the particularities of legal texts
- Implications of the above developments for law students and legal education
Accepted Papers
After submissions and peer review, the following papers have been accepted for presentation at the workshop:
Schedule
- 8:50-9:00. Opening
- 9:00-10:30. Session 1: Rule Parsing, Text Classification, Segmentation
- 9:00-9:30. Deepali Kholkar, Sagar Sunkle and Vinay Kulkarni, Semi-automated creation of regulation rule bases using generic template-driven rule extraction
- 9:30-10:00. Karl Branting, Automating Judicial Document Analysis
- 10:00-10:30. Jaromir Savelka and Kevin D. Ashley, Using Conditional Random Fields to Detect Different Functional Types of Content in Decisions of United States Courts with Example Application to Sentence Boundary Detection
- 10:30-11:00. Coffee break
- 11:00-12:40. Session 2: Neural Models and Corpora
- 11:00-11:30. Son Nguyen Truong, Nguyen Le Minh, Ken Satoh, Tojo Satoshi and Akira Shimazu, Single and multiple layer BI-LSTM-CRF for recognizing requisite and effectuation parts in legal texts
- 11:30-12:00. Kolawole John Adebayo, Luigi Di Caro and Guido Boella, Solving Bar Exams with Deep Neural Networks
- 12:00-12:20. Tommaso Agnoloni, Lorenzo Bacci and Marc van Opijnen, BO-ECLI Parser Engine: the Extensible European Solution for the Automatic Extraction of Legal Links
- 12:20-12:40. Octavia-Maria Sulea, Marcos Zampieri, Mihaela Vela, Josef van Genabith and Liviu P. Dinu, From Robo-Judge to Robo-Lawyer: Exploring the Use of Text Classification in the Legal Domain
- 12:40-14:00. Lunch
- 14:00-14:50. Session 3 - Word Embeddings, Topic Models
- 14:00-14:30. Jörg Landthaler, Bernhard Waltl, Daniel Braun, Dominik Huth, Florian Matthes, Christoph Stocker and Thomas Geiger, Improving Thesauri Using Word Embeddings and a Novel Intersection Method
- 14:30-14:50. James O'Neill, Cecile Robin, Paul Buitelaar and Leona O'Brien, An Analysis of Topic Modelling for Legislative Texts
- 14:50-15:40. Session 4 - Semantics and Default Logic
- 14:50-15:20. Vern Walker, Ashtyn Hemendinger, Nneka Okpara and Tauseef Ahmed,Semantic Types for Decomposing Evidence Assessment in Decisions on Veterans’ Disability Claims for PTSD
- 15:20-15:40. Marcos Pertierra, Sarah Lawsky, Erik Hemberg and Una-May O’Reilly, Towards Formalizing Statute Law as Default Logic through Automatic Semantic Parsing
- 15:40-16:00. Coffee break
- 16:00-17:10. Session 5 - Complexity and Corpora
- 16:00-16:30. Elliott Ash, Massimo Morelli and Matia Vannoni, The Institutional and Political Determinants of Legislative Complexity: a Linguistic Approach
- 16:30-16:50. Kripa Rajshekhar, Wlodek Zadrozny and Sri Sneha Varsha Garapati, Analytics of Patent Case Rulings: Empirical Evaluation of Models for Legal Relevance
- 16:50-17:10. Arjit Srivastava and Navjyoti Singh, A dataset for Indian Legal Judgments: ICJ
- 17:10-18:00. Wrap-up & Discussion
Workshop Format
The workshop will be held on Friday, June 16, from 9am-6pm at the Edmond J. Safra lecture theatre, King's College, London, UK. The exact schedule will be posted soon.
Publication
Selected papers will be published in a special issue of the journal of Artificial Intelligence and Law. Based on the Program Committee’s reviews, authors of selected papers will be invited to expand their papers and submit them for an additional round of reviews and revisions with the goal of publication of a special issue.
Contacts
- Kevin D. Ashley, ashley at pitt dot edu
- Matthias Grabmair, mgrabmai at andrew dot cmu dot edu
Organizing Committee
- Kevin D. Ashley, University of Pittsburgh, USA
- Katie Atkinson, University of Liverpool, UK
- Karl Branting, MITRE Corporation, USA
- Enrico Francesconi, Italian National Research Council (ITTIG-CNR), Publications Office of the European Union
- Matthias Grabmair, Carnegie Mellon University, USA
- Marc Lauritsen, Capstone Practice Systems, Inc., USA
- Vern R. Walker, Maurice A. Deane School of Law at Hofstra University, USA
- Adam Zachary Wyner, University of Aberdeen, UK