The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants

Reasoning is a crucial part of natural language argumentation. To comprehend an argument, one must analyze its warrant, which explains why its claim follows from its premises. As arguments are highly contextualized, warrants are usually presupposed and left implicit. Thus, the comprehension does not only require language understanding and logic skills, but also depends on common sense. In this paper we develop a methodology for reconstructing warrants systematically. We operationalize it in a scalable crowdsourcing process, resulting in a freely licensed dataset with warrants for 2k authentic arguments from news comments. On this basis, we present a new challenging task, the argument reasoning comprehension task. Given an argument with a claim and a premise, the goal is to choose the correct implicit warrant from two options. Both warrants are plausible and lexically close, but lead to contradicting claims. A solution to this task will define a substantial step towards automatic warrant reconstruction. However, experiments with several neural attention and language models reveal that current approaches do not suffice.

[1]  Francis Ferraro,et al.  Script Induction as Language Modeling , 2015, EMNLP.

[2]  Douglas Walton Media argumentation - dialect, persuasion and rhetoric , 2007 .

[3]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[4]  T. Damer,et al.  Attacking Faulty Reasoning: A Practical Guide to Fallacy-Free Arguments , 1980 .

[5]  Jan Snajder,et al.  Fill the Gap! Analyzing Implicit Premises between Claims from Online Debates , 2016, ArgMining@ACL.

[6]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[7]  Bob Carpenter,et al.  The Benefits of a Model of Annotation , 2013, Transactions of the Association for Computational Linguistics.

[8]  Benno Stein,et al.  Argumentation Quality Assessment: Theory vs. Practice , 2017, ACL.

[9]  Mihai Surdeanu,et al.  Two Practical Rhetorical Structure Theory Parsers , 2015, NAACL.

[10]  Tom M. van Engers,et al.  Working on the argument pipeline: Through flow issues between natural language argument, instantiated arguments, and argumentation frameworks , 2016, Argument Comput..

[11]  D. Walton,et al.  Emotive Language in Argumentation , 2014 .

[12]  James B. Freeman,et al.  Argument Structure: Representation and Theory , 2011, Argumentation Library.

[13]  G. Plumer,et al.  Presumptions, Assumptions, and Presuppositions of Ordinary Arguments , 2017 .

[14]  Hector J. Levesque,et al.  The Winograd Schema Challenge , 2011, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning.

[15]  Christopher D. Manning,et al.  NaturalLI: Natural Logic Inference for Common Sense Reasoning , 2014, EMNLP.

[16]  Graeme Hirst,et al.  Classifying arguments by scheme , 2011, ACL.

[17]  S. Toulmin The uses of argument , 1960 .

[18]  Ido Dagan,et al.  Recognizing textual entailment: Rational, evaluation and approaches , 2009, Natural Language Engineering.

[19]  Deirdre Wilson,et al.  Relevance theory: A tutorial , 2002 .

[20]  Bart Verheij,et al.  Handbook of Argumentation Theory , 1987 .

[21]  Douglas Walton,et al.  Using Argumentation Schemes for Argument Extraction: A Bottom-Up Method , 2012, Int. J. Cogn. Informatics Nat. Intell..

[22]  Vivi Nastase,et al.  Enriching Argumentative Texts with Implicit Knowledge , 2017, NLDB.

[23]  Nancy Green Towards Creation of a Corpus for Argumentation Mining the Biomedical Genetics Research Literature , 2014, ArgMining@ACL.

[24]  T. Govier A practical study of argument , 1985 .

[25]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

[26]  R. Rooij,et al.  On Polar Questions , 2003 .

[27]  Iryna Gurevych,et al.  Argumentation Mining in User-Generated Web Discourse , 2016, CL.

[28]  Iryna Gurevych,et al.  C4Corpus: Multilingual Web-size Corpus with Free License , 2016, LREC.

[29]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[30]  R. Amossy The New Rhetoric’s Inheritance. Argumentation and Discourse Analysis , 2009 .

[31]  Nicholas Asher,et al.  NEGATIVE BIAS IN POLAR QUESTIONS , 2005 .

[32]  Chris Reed,et al.  Argumentation Schemes , 2008 .

[33]  Nathanael Chambers,et al.  A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories , 2016, NAACL.

[34]  Sanja Fidler,et al.  Skip-Thought Vectors , 2015, NIPS.

[35]  Paolo Torroni,et al.  Argumentation Mining , 2016, ACM Trans. Internet Techn..

[36]  Saif Mohammad,et al.  SemEval-2016 Task 6: Detecting Stance in Tweets , 2016, *SEMEVAL.

[37]  Akiko Aizawa,et al.  An Analysis of Prerequisite Skills for Reading Comprehension , 2016 .

[38]  Douglas Walton,et al.  Dialog theory for critical argumentation , 2007, Controversis.

[39]  Chris Reed,et al.  Araucaria: Software for Argument Analysis, Diagramming and Representation , 2004, Int. J. Artif. Intell. Tools.

[40]  Vern R. Walker,et al.  Annotating Patterns of Reasoning about Medical Theories of Causation in Vaccine Cases: Toward a Type System for Arguments , 2014, ArgMining@ACL.

[41]  Dirk Hovy,et al.  Learning Whom to Trust with MACE , 2013, NAACL.

[42]  S. E. Newman,et al.  Pushing Toulmin Too Far: Learning From an Argument Representation Scheme , 1998 .

[43]  F. H. Eemeren,et al.  Handbook of Argumentation Theory: A Critical Survey of Classical Backgrounds and Modern Studies , 1987 .