Legal resources such as legislation, public notices, case law, and other legally relevant documents are increasingly freely available on the internet. They are almost entirely presented in natural language and in text. Legal professionals, researchers, and students need to extract and represent information from such resources to support compliance monitoring, analyse cases for case based reasoning, and extract information in the discovery phase of a trial (e-discovery), amongst a range of possible uses. To support such tasks, powerful text analytic tools are available. The tutorial presents an in depth demonstration of one toolkit the General Architecture for Text Engineering (GATE) with examples and several briefer demonstrations of other tools.

Goals

Participants in the tutorial should come away with some theoretical sense of what textual information extraction is about. They will also see some practical examples of how to work with a corpus of materials, develop an information extraction system using GATE and the other tools, and share their results with the research community. Participants will be provided with information on where to find additional materials and learn more.

Intended Audience

The intended audience includes legal researchers, legal professionals, law school students, and political scientists who are new to text processing as well as experienced AI and Law researchers who have used NLP, but wish to get a quick overview of using GATE.

Covered Topics

• Motivations to annotate, extract, and represent legal textual information.
• Uses and domains of textual information extraction. Sample materials from legislation, case decisions, gazettes, e-discovery sources, among others.
• Motivations to use an open source tool for open source development of textual information extraction tools and materials.
• The relationship to the semantic web, linked documents, and data visualisation.
• Linguistic/textual problems that must be addressed.
• Alternative approaches (statistical, knowledge-light, machine learning) and a rationale for a particular bottom-up, knowledge-heavy approach in GATE.
• Outline of natural language processing modules and tasks.
• Introduction to GATE – loading and running simple applications, inspecting the results, refining the search results.
• Development of fragments of a GATE system – lists, rules, and examination of results.
• Discussion of more complex constructions and issues such as fact pattern identification, which is essential for case-based reasoning, named entity recognition, and structures of documents.
• Introduction to ontologies.
• Link textual information extraction to ontologies.
• Introduction to related tools and approaches: C&C/Boxer (parser and semantic interpreter), Attempto Controlled English, scraperwiki, among others.

Date, Time, Location, and Logistics

Monday, June 10, afternoon session. Exact time will be announced as the conference program becomes available.

The tutorial will be held at the Casa dell’Aviatore, viale dell’Università 20 in Rome, Italy.

Information about logistics (conference venue, hotels, travel, etc) is available at the website for the 16th International Conference on Artificial Intelligence and the Law (ICAIL).

Further Information

For further information contact the lecturer.

Lecturer

Dr. Adam Wyner
Lecturer, Department of Computing Science, University of Aberdeen
Aberdeen, Scotland
azwyner at abdn dot ac dot uk
Website

The lecturer has a PhD in Linguistics, a PhD in Computer Science, and research background in computational linguistics. The lecturer has previously given a tutorial on this topic at JURIX 2009 and ICAIL 2011 along with an invited talk at RuleML 2012, has published several conference papers on text analytics of legal resources using GATE and C&C/Boxer, and continues to work on text analysis of legal resources.

A shortlink to this webpage

By Adam Wyner
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Policy proposals are often presented in an encapsulated form (a sound bite). And those receiving it presume that they understand it, the illusion of explanatory depth discussed in a recent article by Frank Keil (a psychology professor at Cornell when and where I was a Linguistics PhD student). This is the illusion where people believe they understand a complex phenomena with greater precision, coherence, and depth than they actually do; they overestimate their understanding. To philosophers, this is hardly a new phenomena, but showing it experimentally is a new result.

In research about public policy, the NY Times authors, Sloman and Fernbach, describe experiments where people state a position and then had to justify it. The results showed that participants softened their views as a result, for their efforts to justify it highlighted the limits of their understanding. Rather than statements of policy proposals, they suggest:

Instead, we voters need to be more mindful that issues are complicated and challenge ourselves to break down the policy proposals on both sides into their component parts. We have to then imagine how these ideas would work in the real world — and then make a choice: to either moderate our positions on policies we don’t really understand, as research suggests we will, or try to improve our understanding.

Breaking down policy proposals into component parts for further investigation and understanding is exactly what we’ve been doing in the IMPACT Project.

This article and the references to further literature are not only intrinsically interesting, but they also give me additional ways of thinking about these issues and an evaluative paradigm for our tools.

The talk, Arguing from a Point of View, addresses the issue of extracting argumentative information from web-based information sources such as consumer product reviews or recommendations. Jodi Schneider is a co-author. The paper is available on the previous post. Some of the topics are developed further in our paper at SWAIE 2012.

Shortlink to this page.

By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

A Model-Based Critique Tool for Policy Deliberation
Adam Wyner, Maya Wardeh, Trevor Bench-Capon, and Katie Atkinson

Abstract
Domain models have proven useful as the basis for the construction and evaluation of arguments to support deliberation about policy proposals. Using a model provides the means to systematically examine and understand the fine-grained objections that individuals might have about the policy. While in previous approaches, a justification for a policy proposal is presented for critique by the user, here, we reuse the domain model to invert the roles of the citizen and the government: a policy proposal is elicited from the citizen, and a software agent automatically and systematically critiques it relative to the model and the government’s point of view. Such an approach engages citizens in a critical dialogue about the policy actions, which may lead to a better understanding of the implications of their proposals and that of the government. A web-based tool that interactively leads users through the critique is presented.

Bibtex
@INPROCEEDINGS{WynerEtAlCritique2012,
author = {Adam Wyner and Wardeh, Maya and Trevor Bench-Capon and Katie Atkinson},
title = {A Model-Based Critique Tool for Policy Deliberation},
booktitle = {Proceedings of 25th International Conference on Legal Knowledge and Information Systems (JURIX 2012)},
year = {2012},
pages = {xx-xx},
address = {Amsterdam},
publisher = {IOS Press},
note = {To appear},
comment = {Legal Knowledge and Information Systems. Jurix 2012: The AA-th Annual Conference}
}

An Empirical Approach to the Semantic Representation of Laws
Adam Wyner, Johan Bos, Valerio Basile, and Paulo Quaresma

Abstract
To make legal texts machine processable, the texts may be represented as linked documents, semantically tagged text, or translated to formal representations that can be automatically reasoned with. The paper considers the latter, which is key to testing consistency of laws, drawing inferences, and providing explanations relative to input. To translate laws to a form that can be reasoned with by a computer, sentences must be parsed and formally represented. The paper presents the state-of-the-art in automatic translation of law to a machine readable formal representation, provides corpora, outlines some key problems, and proposes tasks to address the problems.

Bibtex
@INPROCEEDINGS{WynerEtAlSemanticRep2012,
author = {Adam Wyner and Bos, Johan and Valerio Basile and Paulo Quaresma},
title = {An Empirical Approach to the Semantic Representation of Law},
booktitle = {Proceedings of 25th International Conference on Legal Knowledge and Information Systems (JURIX 2012)},
year = {2012},
pages = {xx-xx},
address = {Amsterdam},
publisher = {IOS Press},
note = {To appear}
}

Shortlink to this page.

By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

The Oxford Internet Institute was founded in 2001 at the University of Oxford, as an academic centre for the study of the societal implications of the Internet.

In the last forty years the Internet has grown from an arcane and specialized academic service to the sophisticated global network of networks we see today: during this period the complexity of its societal implications has become ever more obvious, as well as the many ways it shapes our lives. Grounded in a determination to measure, understand and explain the Internet’s multi-faceted interactions and effects, our research projects bring together some of the best international scholars within a multi-disciplinary department in one of the world’s top research universities. We are committed to being an informed, independent and nonpartisan source of the highest quality analysis and insight in all our research and policy-related activities.

The institute recently organised a conference on Internet, Politics, Policy 2012: Big Data, Big Challenges, where there were some papers bearing on policy-making. These are topics closely related to research that I do. An organisation worth following in the future.

One grain of sand is not a heap of sand; two grains of sand are not a heap of sand; …. ; adding one more grain of sand to some sand is not enough to make a heap of sand; yet, at some point, we agree we have a heap of sand.

So, where are the boundaries?

Part of what is interesting to me is that while we might have problems to provide a formal, systematic analysis, we seem to have strong intuitions that are (more or less, and in fact more, where all things are otherwise equal) in agreement with the intuitions of others.

In law, such issues about vagueness also arise, and they lead to legal contention, so are important to decide. In this radio broadcast, there is a fun discussion of the sorities paradoxes and some mention of how legislators address them; in particular, just how can legislators ‘define’ nudity?

Analysis Extra: The Philosopher’s Arms: Sorites’ Heap 10 Sep 2012

The program is about 30 minutes long and should play in your browser. The broadcast content is copyright the BBC. Radio 4 is great!

The school aims at providing knowledge of the most significant ICT standards emerging for legislation, judiciary, parliamentary and administrative documents. The course provides understanding of their impact in the different phases of the legislative and administrative process, awareness of the tools based on legal XML standards and of their constellations, and the ability to participate in the drafting and use of standard-compliant documents throughout law-making process. In particular we would like to create consciousness in the stakeholders in the legal domain about the benefits and the possibilities provided by the correct usage of Semantic Web technologies such as XML standards, ontologies, natural language processing techniques applied to legal texts, legal knowledge modelling and reasoning tools.

The zipped file contains the slides and some exercise material.

The first lecture (Part 1) introduces the general topic, some samples of results, and a discussion about crowdsourcing annotations in legal cases. The second lecture (Part 2) discusses the parsing and semantic representation of a fragment of the British Nationality Act. The class materials are used for an in class exercise about annotation.

Shortlink to this page.

By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Identifying Consumers’ Arguments in Text
Jodi Schneider and Adam Wyner

Abstract
Product reviews are a corpus of textual data on consumer opinions. While reviews can be sorted by rating, there is limited support to search in the corpus for statements about particular topics, e.g. properties of a product. Moreover, where opinions are justified or criticised, statements in the corpus indicate arguments and counterarguments. Explicitly structuring these statements into arguments could help better understand customers’ disposition towards a product. We present a semi-automated, rule-based information extraction tool to support the identification of statements and arguments in a corpus, using: argumentation schemes; user, domain, and sentiment terminology; and discourse indicators.

Bibtex
@INPROCEEDINGS{WynerSchneiderSWAIE2012,
author = {Jodi Schneider and Adam Wyner},
title = {Identifying Consumers’ Arguments in Text},
booktitle = {Proceedings of the 1st Workshop on Semantic Web and Information Extraction (SWAIE 2012)},
year = {2012},
address = {Galway, Ireland},
note = {To appear}}

Shortlink to this page.

By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Semi-Automated Argumentation Analysis of Online Product Reviews

Shortlink to this page.

By Adam Wyner

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.