Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network

With the advancement in argument detection, we suggest to pay more attention to the challenging task of identifying the more convincing arguments. Machines capable of responding and interacting with humans in helpful ways have become ubiquitous. We now expect them to discuss with us the more delicate questions in our world, and they should do so armed with effective arguments. But what makes an argument more persuasive? What will convince you? In this paper, we present a new data set, IBM-EviConv, of pairs of evidence labeled for convincingness, designed to be more challenging than existing alternatives. We also propose a Siamese neural network architecture shown to outperform several baselines on both a prior convincingness data set and our own. Finally, we provide insights into our experimental results and the various kinds of argumentative value our method is capable of detecting.

[1]  Sarit Kraus,et al.  Providing Arguments in Discussions on the Basis of the Prediction of Human Argumentative Behavior , 2016, ACM Trans. Interact. Intell. Syst..

[2]  Wei Chu,et al.  Preference learning with Gaussian processes , 2005, ICML.

[3]  Tie-Yan Liu,et al.  Learning to rank: from pairwise approach to listwise approach , 2007, ICML '07.

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

[5]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[6]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[7]  B. J. Fogg,et al.  A behavior model for persuasive design , 2009, Persuasive '09.

[8]  T. Brock,et al.  Journal of Personality and Social Psychology the Role of Transportation in the Persuasiveness of Public Narratives Text Quality Individual Differences and Situational Influences Transportation Scale Items Gender Differences Discriminant Validation: Need for Cognition Effect of Text Manipulation Beli , 2022 .

[9]  Cristian Danescu-Niculescu-Mizil,et al.  Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions , 2016, WWW.

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  J. A. Blair,et al.  Logical Self-Defense , 1977 .

[12]  O. Oha.  Fallacies , 2005 .

[13]  Chris Callison-Burch,et al.  Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims , 2019, NAACL.

[14]  Beate Baltes,et al.  Assessing Quality of Critical Thought in Online Discussion , 2009 .

[15]  Brent Brossmann.  Fallacies and Argument Appraisal , 2006 .

[16]  M. Pigliucci,et al.  The Fake, the Flimsy, and the Fallacious: Demarcating Arguments in Real Life , 2015 .

[17]  Gert R. G. Lanckriet,et al.  Metric Learning to Rank , 2010, ICML.

[18]  Aaron C. Courville,et al.  Recurrent Batch Normalization , 2016, ICLR.

[19]  Kathleen McKeown,et al.  Persuasive Influence Detection: The Role of Argument Sequencing , 2018, AAAI.

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

[21]  Iryna Gurevych,et al.  Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM , 2016, ACL.

[22]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[23]  Iryna Gurevych,et al.  Exploiting Debate Portals for Semi-Supervised Argumentation Mining in User-Generated Web Discourse , 2015, EMNLP.

[24]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[25]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[26]  A. Vinokur,et al.  Persuasive argumentation and social comparison as determinants of attitude polarization , 1977 .

[27]  B. J. Fogg,et al.  Persuasive computers: perspectives and research directions , 1998, CHI.

[28]  Claire Cardie,et al.  Exploring the Role of Prior Beliefs for Argument Persuasion , 2018, NAACL.

[29]  B. J. Fogg,et al.  Persuasive technology: using computers to change what we think and do , 2002, UBIQ.

[30]  Iryna Gurevych,et al.  Parsing Argumentation Structures in Persuasive Essays , 2016, CL.

[31]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[32]  Iryna Gurevych,et al.  Annotating Argument Components and Relations in Persuasive Essays , 2014, COLING.

[33]  D. O’Keefe.  Conviction, Persuasion, and Argumentation: Untangling the Ends and Means of Influence , 2012 .

[34]  Iryna Gurevych,et al.  Finding Convincing Arguments Using Scalable Bayesian Preference Learning , 2018, TACL.

[35]  Vincent Ng,et al.  Why Can't You Convince Me? Modeling Weaknesses in Unpersuasive Arguments , 2017, IJCAI.

[36]  Iryna Gurevych,et al.  What makes a convincing argument? Empirical analysis and detecting attributes of convincingness in Web argumentation , 2016, EMNLP.

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

[38]  Anna Rumshisky,et al.  Towards Debate Automation: a Recurrent Model for Predicting Debate Winners , 2017, EMNLP.

[39]  Alessandro Moschitti,et al.  Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks , 2015, SIGIR.

[40]  Benno Stein,et al.  Using Argument Mining to Assess the Argumentation Quality of Essays , 2016, COLING.

[41]  Eyal Shnarch,et al.  Will it Blend? Blending Weak and Strong Labeled Data in a Neural Network for Argumentation Mining , 2018, ACL.

[42]  Noam Slonim,et al.  A Benchmark Dataset for Automatic Detection of Claims and Evidence in the Context of Controversial Topics , 2014, ArgMining@ACL.

[43]  Noam Slonim,et al.  Context Dependent Claim Detection , 2014, COLING.

[44]  Debanjan Ghosh,et al.  Coarse-grained Argumentation Features for Scoring Persuasive Essays , 2016, ACL.

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

[46]  Mitesh M. Khapra,et al.  Show Me Your Evidence - an Automatic Method for Context Dependent Evidence Detection , 2015, EMNLP.