Skip to the content of the web site.

CS499R/CS698 | Argumentation Mining Reading Course/

General Interest Reading Seminar Fall 2015

CS499R/CS698 Argumentation Mining Reading Course/Reading Seminar

Seminar Coordinator: Chrysanne Di Marco
Meeting Time: Fridays 12:15-1:15 (starting October 2)
Location: DC1316


CS499R/CS698 meetings will be held with the Argumentation Mining Reading Seminar.
Weekly individual CS499R student meetings will also be arranged.
Readings will be available online, DC Library reserve, or from the seminar coordinator.

Course Overview

This course will be a reading course and seminar group covering key texts and papers in Argumentation Mining, a challenging new field of study in corpus-based discourse analysis. Argumentation Mining has emerged as a major field of research within the past 10 years. Although Argumentation Mining can be viewed as a subfield of Natural Language Processing (NLP), its applications are generally more sophisticated and require deeper understanding of text than is the case for most current NLP systems, which typically rely on shallow forms of text analysis.

Argumentation is an intrinsic part of human intelligence and reasoning, not only in formal situations like understanding reasoning in scientific articles or legal texts, but in everyday life, where we constantly express our own, and evaluate others', sentiments and opinions, interpret media, judge politicians, and so forth, in order to understand situations and make appropriate decisions.

Argumentation Mining is inherently multidisciplinary and is bringing together researchers and practitioners from many areas, including: Philosophy, Logic, Linguistics, Argumentation Theory, Computational Linguistics, Computer Science, Cognitive Science, Artificial Intelligence, and Machine Learning.

What is "Argumentation"?

Formally, argumentation is akin to mathematical proof, but in everyday life situations this degree of rigorous proof is usually not possible, so we must rely on informal proof, i.e., chains of logical reasoning built up through the argumentation structure in a text or utterance.

What makes Argumentation Mining particularly challenging is that it requires complex and detailed annotation of high-quality text corpora from many specialized domains, each with its own vocabulary, ontologies, and implicit background knowledge needed for understanding texts in its field.

Course Requirements

Nature of the readings

We will cover both theoretical background material and computational applications.

Topics will include: formal and linguistic models of argumentation; informal logic; computational discourse models; applications in biomedical and scientific information extraction; analysis of narrative and social media; reasoning about trust in information; argumentation in unexpected places (music, stories, ...).

What is expected of participants

Participants will be expected to read widely and in-depth. There are no formal requirements other than interest in the topic and ability to read and analyze technical material, to present oral summaries, and to take part in group discussions.

Participants attending informally (i.e., not for academic credit) are welcome to sit in on as few or as many sessions as they wish, but it is expected that all those who attend take an active role in discussions, and present at least one reading.

Grading breakdown (if participating for academic credit)

Session 1: Organizational Meeting/Prologue

Friday October 2, 12:15-1:15, DC1316

Background reading

Jay Heinrichs, "Thank you for arguing: What Aristotle, Lincoln, and Homer Simpson can teach us about the art of persuasion", Three Rivers Press, revised edition, 2013

All participants in the reading course and reading seminar will receive a copy

Session 2: Classical Models of Argumentation

Friday October 9, 12:15-1:15, DC1316

Theoretical background

Stephen E. Toulmin, The uses of argument, Cambridge University Press, second edition, 2003

Available online through UW Library


Readings

Chapter III The Layout of Arguments

Computational argumentation

Raquel Mochales Palau and Marie-Francine Moens, "Argumentation mining: The detection, classification and structure of arguments in text", ICAIL-2009, Barcelona, Spain

PDF

Session 3: Rhetorical Models of Argumentation

Friday October 16, ***12:00-1:00***, DC1316

Theoretical background

Christopher W. Tindale, Acts of arguing: A rhetorical model of argument, State University of New York Press, 1999

DC Library Short-term loan call number: UWD XXXX


Readings

Introduction: The Case for Rhetorical Argumentation
Chapter 3: Contexts and Arguments: An Introduction to the Rhetorical Perspective
Chapter 5: Case Studies in Rhetorical Argumentation (5.1)

Computational argumentation

William C. Mann and Sandra A. Thompson, "Rhetorical structure theory: Toward a functional theory of text organization", Text, 8(3), 1988, pp243-281

Available from University of Waterloo Library e-journals

Nancy Green, "Representation of argumentation in text with Rhetorical Structure Theory", Argumentation, 24(2), 2010, pp181-196

Available from University of Waterloo e-journals

Session 4: Argumentation Schemes I

Friday October 23, 12:15-1:15, DC1316

Theoretical background

Chaim Perelman and Lucie Olbrechts-Tyteca, The new rhetoric: A treatise on argumentation, University of Notre Dame Press, 1969

Available from seminar coordinator


Reading:

Part One: The Framework of Argumentation
Chapters 1-7, pages 13-35

Part Two: The Starting Point of Argument
I. Agreement, Chapters 15-17, pages 65-74
III. Presentation of Data and Form of the Discourse, Chapter 41 Rhetorical Figures and Argumentation, pages 167-171

Part Three: Techniques of Argumentation
II. Arguments Based on the Structure of Reality, some of Chapters 60-62, pages 261-267
V. The Interaction of Arguments, Chapter 103 Order and Persuasion, pages 490-495

Reading

S. Parsons, K. Atkinson, Z. Li, P. McBurney, E. Sklar, M. Singh, K. Haigh, K. Levitt, J. Rowe, "Argument schemes for reasoning about trust", Argument & Computation, 2014, 5(2-3), pp160-190

Available from University of Waterloo e-journals


Session 5: Argumentation Schemes II

Friday November 6 and 13, 12:15-1:15, DC1316

Theoretical background

Douglas Walton and Christopher Reed, Argumentation schemes, Cambridge University Press, 2008

Copies available from seminar coordinator


Readings:

Chapter 1: Basic Tools in the State of the Art (6.1)
Chapter 2: Schemes for Argument from Analogy, Classification, and Precedent
Chapter 6: Schemes and Enthymemes (6.1-6.2, 6.5-6.7)
Chapter 8: The History of Schemes (review only)
Chapter 9: A User's Compendium of Schemes (reference only)

Computational argumentation

C.A. Reed and G.W.A. Rowe, "Araucaria: Software for argument analysis, diagramming and representation", International Journal of AI Tools, 2004, 13(4), pp961-980

Available at:


http://www.arg.dundee.ac.uk/people/chris/publications/showbyyear.php

Session 6: Argumentation Mining in Stories and Social Media

Friday November 20, 12:15-1:15, DC1316

Floris Bex and Trevor Bench-Capon, "Understanding narratives with argumentation", Computational models of argument, S.Parsons et al. (eds.), IOS Press, 2014

Rolando Medellin, Chris Reed and Vicki Hanson, "Spoken interaction with broadcast debates", Computational models of argument, S.Parsons et al. (eds.), IOS Press, 2014

Above readings available from seminar coordinator


Elena Cabrio and Serena Villata, "A natural language bipolar argumentation approach to support users in online debate interactions", Argument & Computation, 4:3, 209-230, 2013

Above reading available from University of Waterloo Library e-journals


Session 7: Argumentation in Unexpected Places

Friday December 4, 12:15-1:15, DC1316

Patrick Saint-Dizier, "Some aspects of a preliminary analysis of argumentation in Western tonal music", Computational Models of Natural Argument (CMNA) Workshop, Montpellier, August 2012

PDF

Peter Novak and Cees Witteveen, "Context-aware reconfiguration of large-scale surveillance systems: Argumentative approach", Argument & Computation, 2015, 6(1), pp3-23

Available from University of Waterloo Library e-journals


From the Abstract:


"The Metis research project aims at supporting maritime safety and security by facilitating continuous monitoring of vessels in national coastal waters and prevention of phenomena, such as vessel collisions, environmental hazard, or detection of malicious intents, such as smuggling. Surveillance systems such as Metis typically comprise a number of heterogeneous information sources and information aggregators. ... We model information-aggregation systems as networks of inter-dependent reasoning agents, each representing a mechanism for justification/refutation of a conclusion derived by the agent. [...]".

Session 8: Biomedical Argumentation Mining

Friday December 11, 12:15-1:15, DC1316

Theoretical background (review only)

Greg Myers, "The pragmatics of politeness in scientific articles", Applied Linguistics, 1989, 10(1), pp1-35

Available from University of Waterloo Library e-journals

Computational argumentation

Nancy L. Green, "Argumentation for scientific claims in a biomedical research article", of the Workshop on Frontiers and Connections between Argumentation Theory and Natural Language Processing (ArgNLP 2014), Forli-Cesena, Italy, July 21-25, 2014.

Available from the seminar coordinator

Session 9: Scientific Argumentation Mining

JANUARY DATE TBA

Theoretical background

John Swales, Research genres: Explorations and applications, Cambridge University Press, 2004 - "Create-A-Research-Space" (CARS) model of the argumentative moves authors use in research-article introductions

Available from the seminar coordinator


Readings

See: Index, "Create-a-Research-Space" pages

Budsaba Kanoksilapatham, A corpus-based investigation of scientific research articles: Linking move analysis with multidimensional analysis, PhD dissertation, Department of Linguistics, Georgetown University, 2003

Available from seminar coordinator


Readings

TBA

Computational argumentation

Simone Teufel, The structure of scientific articles: Applications to citation indexing and summarization, CSLI Publications, 2010

Available from seminar coordinator


Readings

TBA

Session 10: Cognitive Models of Argumentation

JANUARY DATE TBA

Artur S. d'Avila Garcez, Dov M. Gabbay, Luis C. Lamb, "A neural cognitive model of argumentation with application to legal inference and decision making", Journal of Applied Logic, 2014, 12(2), pp109-127

Available from University of Waterloo Library e-journals


From the Abstract:


"Formal models of argumentation have been investigated in several areas, from multi-agent systems and artificial intelligence (AI) to decision making, philosophy and law. In artificial intelligence, logic-based models have been the standard for the representation of argumentative reasoning. More recently, the standard logic-based models have been shown equivalent to standard connectionist models. This has created a new line of research where (i) neural networks can be used as a parallel computational model for argumentation and (ii) neural networks can be used to combine argumentation, quantitative reasoning and statistical learning. In this paper, we propose a connectionist cognitive model of argumentation that accounts for both standard and non-standard forms of argumentation. ... [Our] approach opens up two new perspectives in the short-term: the use of neural networks for computing prevailing arguments efficiently through the propagation in parallel of neuronal activations, and the use of the same networks to evolve the structure of the argumentation network through learning (e.g. to learn the strength of arguments from data)."

Final Session: Wrapup/ Roundtable/ Epilogue

JANUARY DATE TBA

Roundtable Discussion

Current projects in computational rhetoric, computational argumentation, and argumentation mining at the University of Waterloo, The University of Western Ontario, and the University of Dundee.

Epilogue: "W(h)ither Human Argumentation??"

Background reading

Nicholas Carr, "Is Google making us stupid?, The Atlantic, 2008

Available at:


http://nicholascarr.com/

The future of human cognition?

Nicholas Carr, The shallows: What the Internet is doing to our brains, W.W. Norton & Company, 2011

All regular participants in the reading course and seminar will receive a copy