Classifying arguments by scheme

From AcaWiki
Jump to: navigation, search

Citation: Vanessa Wei Feng and Graeme Hirst (2011) Classifying arguments by scheme. HLT (RSS)
Internet Archive Scholar (search for fulltext): Classifying arguments by scheme
Tagged: Computer Science (RSS) machine learning (RSS), argumentation schemes (RSS), argumentation mining (RSS)


The goal is to automatically identify Walton's Argumentation schemes. The approach is machine learning, using Argument research corpus as a training set.

The authors work with 5 schemes and report "We achieve accuracies of 63–91% in one-against-others classification and 80–94% in pairwise classification (baseline of 50% in both cases)."

Schemes used

  1. Argument from example
  2. Argument from cause to effect
  3. Practical reasoning
  4. Argument from consequences
  5. Argument from verbal classification

Selected References

Cited related work

Raquel Mochales' thesis work; the following are cited (others are covered elsewhere on Acawiki):

  • Marie-Francine Moens, Erik Boiy, Raquel Mochales Palau, and Chris Reed. 2007. Automatic detection of arguments in legal texts. In ICAIL ’07: Proceedings of the 11th International Conference on Artificial Intelligence and Law, pages 225–230, New York, NY, USA. ACM.

Theoretical and Practical Relevance

In my view, this points to a need for a real gold standard argumentation corpus.

Mentioned by scholars

Extended version (Master's thesis)

Vanessa Wei Feng. 2010. Classifying arguments by scheme (MSc thesis). Technical report, Department of Computer Science, University of Toronto, November.