Category: argumentation

Computational Argumentation on the Web with Natural Language

Over the last four years, I have been working on topics related to computational argumentation on the web using natural language. Some of my publications and previous postings reflect these interests. Along with my colleague Tom van Engers, I prepared two research proposals on this topic, which are here presented as technical reports of our work. These reports are also relevant to the current IMPACT project, which addresses many of the same themes.
There is a short paper (five pages) which outlines key ideas, but has little in the way of discussion or background discussion. There is a long paper (28 pages) which goes into the proposal in much more depth.
Comments and discussion on these documents are very welcome.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

Research Fellow at University of Leeds

On May 4, I’m taking up a research fellow position. I’ll continue to work on the IMPACT Project:

IMPACT will conduct original research to develop and integrate formal, computational models of policy and arguments about policy, to facilitate deliberations about policy at a conceptual, language-independent level.

I’ll be based at the University of Leeds, Institute of Communication Studies, in the Centre for Digital Citizenship:

The CdC’s mission is to promote outstanding research on the changing nature of citizenship in a digitally networked society and to contribute to the analysis and development of policy in this area.

I’ll be working with Ann Macintosh:

My research agenda falls within two main socio-technical areas of interest. The first concerns the societal effect of technology on governance processes and the development of an evaluation framework for eParticipation. This area of my research is providing high-level insights into the mechanisms that need to be built into future online participation systems to appreciate how, where and why people use them. My second research area is the support for citizen engagement in policy making and the provision of public agency information and knowledge. Here the focus is on the use of Web 2.0 and computer supported argumentation systems to support deliberation and knowledge sharing.

Looking forward to working on these topics!
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

Recent Paper Submissions

During my time at the Leibniz Center for Law working on the IMPACT, I and my colleagues Tom van Engers and Kiavash Bahreini prepared and submitted three papers to conferences and workshops. The drafts of the papers are linked below along with the abstracts. Comments welcome.
A Framework for Enriched, Controlled On-line Discussion Forums for e-Government Policy-making
Adam Wyner and Tom van Engers
Submitted to eGOV 2010
Abstract
The paper motivates and proposes a framework for enriched on-line discussion forums for e-government policy-making, where pro and con statements for positions are structured, recorded, represented, and evaluated. The framework builds on current technologies for multi-threaded discussion lists by integrating modes, natural language processing, ontologies, and formal argumentation frameworks. With modes other than the standard reply “comment”, users specify the semantic relationship between a new statement and the previous statement; the result is an argument graph. Natural language processing with a controlled language constrains the domain of discourse, eliminates ambiguity and unclarity, allows a logical representation of statements, and facilitates information extraction. However, the controlled language is highly expressive and natural . Ontologies represent the knowledge of the domain. Argumentation frameworks evaluate the argument graph and generate sets of consistent statements. The output of the system is a rich and articulated representation of a set of policy statements which supports queries, information extraction, and inference
From Policy-making Statements to First-order Logic
Adam Wyner, Tom van Engers, and Kiavash Bahreini
Submitted to eGOVIS 2010
Abstract
Within a framework for enriched on-line discussion forums for e-government policy-making, pro and con statements for positions are input, structurally related, then logically represented and evaluated. The framework builds on current technologies for multi-threaded discussion, natural language processing, ontologies, and formal argumentation frameworks. This paper focuses on the natural language processing of statements in the framework. A small sample policy discussion is presented. We adopt and apply a controlled natural language (Attempto Controlled English) to constrain the domain of discourse, eliminate ambiguity and unclarity, allow a logical representation of statements which supports inference and consistency checking, and facilitate information extraction. Each of the polity statements is automatically translated into rst-order logic. The result is logical representation of the policy discussion which we can query, draw inferences (given ground statements), test for consistency, and extract detailed information.
Towards Web-base Mass Argumentation in Natural Language
Adam Wyner and Tom van Engers
Submitted to EKAW 2010
Abstract
Within the artificial intelligence community, argumentation has been studied for quite some years now. Despite progress, the field has not yet succeeded in creating support tools that members of the public could use to contribute their views to discussions of public policy. One important reason for that is that the input statements of participants in policy-making discussions are put forward in natural language, while translating the statements into the formal models used by argumentation scientists is cumbersome. These formal models can be used to automatically reason with, query, or transmit domain knowledge using web-based technologies. Making this knowledge explicit, formal, and expressed in a language which a machine can process is a labour, time, and knowledge intensive task. To make such translation and it requires expertise that most participants in policy-making debates do not have. In this paper we describe an approach with which we aim at contributing to a solution of this knowledge acquisition bottle-neck. We propose a novel, integrated methodology and framework which adopts and adapts existing technologies. We use semantic wikis which support mass, collaborative, distributive, dynamic knowledge acquisition. In particular, ACEWiki incorporates NLP tools, enabling linguistically competent users to enter their knowledge in natural language, while yielding a logical form that is suitable for automated processing. In the paper we will explain how we can extend the ACEWiki and augment it with argumentation tools which elicit knowledge from users, making implicit information explicit, and generate subsets of consistent knowledge bases from inconsistent knowledge bases. To a set of consistent propositions, we can apply automated reasoners, allowing users to draw inferences and make queries. The methodology and framework take a fragmentary, incremental development approach to knowledge acquisition in complex domains.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

The IMPACT Project — first two days

As I mentioned in a previous post, I am working in Amsterdam for the next three months on setting up a research project at the Leibniz Center for Law. The focus here is to develop information extract of textual debates (using GATE) and a tool for inputting debates in a structured manner that can be further processed for reasoning.
The official IMPACT Project information on CORDIS.
As part of my contribution, I have two draft papers, written in the spring and summer of 2009, which will be further developed at Leibniz: From Arguments in Natural Language to Argumentation Frameworks and Multi-modal Multi-threaded Online Forums. While these are early drafts of papers and not for wider circulation, they give a good indication of the line of thinking and of some of the key ideas we will be pursuing. Comments about these works are very welcome.
By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

Research on Argumentation at the Leibniz Center for Law in Amsterdam

I have a 3 month research job at the Leibniz Center for Law, University of Amsterdam starting February 1 and working with Tom van Engers. This is part of the IMPACT project:

IMPACT is an international project, partially funded by the European Commission under the 7th framework programme. It will conduct original research to develop and integrate formal, computational models of policy and arguments about policy, to facilitate deliberations about policy at a conceptual, language-independent level. To support the analysis of policy proposals in an inclusive way which respects the interests of all stakeholders, research on tools for reconstructing arguments from data resources distributed throughout the Internet will be conducted. The key problem is translation from these sources in natural language to formal argumentation structures, which will be input for automatic reasoning.

My role will be to set up a Ph.D. research project concerning the key problem. This is based on an unsuccessful larger research proposal that I made with Tom. I’ll be organising the database, the literature, some of the software, and outlining the approach the student would take. I’ll make notes on the progress as it happens.
I’m looking forward to living for a while in Amsterdam, working with Tom and my other colleagues at the center — Joost Breuker, Rinke Hoekstra, Emile de Maat. The Netherlands also has a very lively Department of Argumentation Theory. As an added bonus, my colleagues from Linguistics, Susan Rothstein and Fred Landman, are in Amsterdam on sabbatical. Will be a very interesting and fun period.

New publication on Text Mining

I and my colleagues have a paper forthcoming in Semantic Processing of Legal Texts (S. Montemagni, D. Tiscornia, and E. Francesconi, eds.), Lecture Notes in Computer Science, Springer, 2009. Below please find a link to the paper and an abstract.
Cheers,
Adam Wyner
Approaches to text mining arguments from legal cases
Adam Wyner
University College London
Rachel Mochales-Palau and Marie-Francine Moens
Katholieke Universiteit Leuven
David Milward
Linguamatics, LTD.
Abstract
This paper describes recent approaches using text-mining to automatically profile and extract arguments from legal cases. We outline some of the background context and motivations. We then turn to consider issues related to the construction and composition of a corpora of legal cases. We show how a Context-Free Grammar can be used to extract arguments, and how ontologies and Natural Language Processing can identify complex information such as case factors and participant roles. Together the results bring us closer to automatic identification of legal arguments.

Annotating Rules in Legislation

Over the last couple of months, I have had discussions about text mining and annotating rules in legislation with several people (John Sheridan of The Office of Public Sector Information, Richard Goodwin of The Stationery Office, and John Cyriac of Compliance Track). While nothing yet concrete has resulted from these discussions, it is clearly a “hot topic”.
In the course of these discussions, I prepared a short outline of the issues and approaches, which I present below. Comments, suggestions, and collaborations are welcome.
Vision, context, and objectives
One of the main visions of artificial intelligence and law has been to develop a legislative processing tool. Such a tool has several related objectives:

      [1.] To guide the drafter to write well-formed legal rules in natural language.
      [2.] To automatically parse and semantically represent the rules.
      [3.] To automatically identify and annotate the rules so that they can be extracted from a corpus of legislation for web-based applications.
      [4.] To enable inference, modeling, and consistency testing with respect to the rules.
      [5.] To reason with respect to domain knowledge (an ontology).
      [6.] To serve the rules on the web so that users can use natural language to input information and receive determinations.

While no such tool exists, there has been steady progress on understanding the problems and developing working software solutions. In early work (see The British nationality act as a logic program (1986)), an act was manually translated into a program, allowing one to draw inferences given ground facts. Haley is a software and service company which provides a framework which partially addresses 1, 2, 4, and 6 (see Policy Automation). Some research addresses aspects of 3 (see LKIF-Core Ontology). Finally, there are XML annotation schemas for legislation (and related input support) such as The Crown XML Schema for Legislation and Akoma Ntoso, both of which require manual input. Despite these advances, there is much progress yet to be made. In particular, no results fulfill [3.].
In consideration of [3.], the primary objective of this proposal is to use the General Architecture for Text Engineering (GATE) framework in order to automatically identify and annotate legislative rules from a corpus. The annotation should support web-based applications and be consistent with semantic web mark ups for rules, e.g. RuleML. A subsidiary objective is to define an authoring template which can be used within existing authoring applications to manually annotate legislative rules.
Benefits
Attaining these objectives would:

  • Support automated creation, maintenance, and distribution of rule books for compliance.
  • Contribute to the development of a legislative processing tool.
  • Make legislative rules accessible for web-based applications. For example, given other annotations, one could identify rules that apply with respect to particular individuals in an organisation along with relevant dates, locations, etc.
  • Enable further processing of the rules such as removing formatting, parsing the content of the rules, and representing them semantically.
  • Allow an inference engine to be applied over the formalised rule base.
  • Make legislation more transparent and communicable among interested parties such as government departments, EU governments, and citizenry.

Scope
To attain the objectives, we propose the following phases, where the numbers represent weeks of effort:

  • Create a relatively small sample corpus to scope the study.
  • Manually identify the forms of legislative rules within the corpus.
  • Develop or adapt an annotation scheme for rules.
  • Apply the analysis tools of GATE and annotate the rules.
  • Validate that GATE annotates the rules as intended.
  • Apply the annotation system to a larger corpus of documents.

For each section, we would produce a summary of results, noting where difficulties are encountered and ways they might be addressed.
Extending the work
The work can be extended in a variety of ways:

  • Apply the GATE rules to a larger corpus with more variety of rule forms.
  • Process the rules for semantic representation and inference.
  • Take into consideration defeasiblity and exceptions.
  • Develop semantic web applications for the rules.

By Adam Wyner
Distributed under the Creative Commons
Attribution-Non-Commercial-Share Alike 2.0

New publication in AAAI Symposium

I and my colleagues have a paper forthcoming in the proceedings of the AAAI Fall Symposium (November 2009) The Uses of Computational Argumentation. Trevor will have the honours of making the presentation at the symposium. Below please find a link to the paper and an abstract.
Cheers,
Adam Wyner
Instantiating Knowledge Bases in Abstract Argumentation Frameworks
Adam Wyner
University College London
Trevor Bench-Capon and Paul Dunne
University of Liverpool
Abstract
Abstract Argumentation Frameworks (AFs) provide a fruitful basis for exploring issues of defeasible reasoning. Their power largely derives from the abstract nature of the arguments within the framework, where arguments are atomic nodes in an undifferentiated relation of attack. This abstraction conceals different conceptions of argument, and concrete instantiations encounter difficulties as a result of conflating these conceptions. We distinguish three distinct senses of the term. We provide an approach to instantiating AFs in which the nodes are restricted to literals and rules, encoding the underlying theory directly. Arguments, in each of the three senses, then emerge from this framework as distinctive structures of nodes and paths. Our framework retains the theoretical and computational benefits of an abstract AF, while keeping notions distinct which are conflated in other approaches to instantiation.