Bias in semantic and discourse interpretation

In this paper, we show how game-theoretic work on conversation combined with a theory of discourse structure provides a framework for studying interpretive bias. Interpretive bias is an essential feature of learning and understanding but also something that can be used to pervert or subvert the truth. The framework we develop here provides tools for understanding and analyzing the range of interpretive biases and the factors that contribute to them.

[1]  Prashant Parikh,et al.  Pragmatics and Games of Partial Information , 2006 .

[2]  Krishnendu Chatterjee.  Concurrent games with tail objectives , 2007, Theor. Comput. Sci..

[3]  Nicholas Asher,et al.  Evaluation in Discourse: a Corpus-Based Study , 2016, Dialogue Discourse.

[4]  J. Harsanyi.  GAMES WITH INCOMPLETE INFORMATION PLAYED BY “BAYESIAN” PLAYERS , 2020, Classics in Game Theory.

[5]  Solon Barocas,et al.  Language (Technology) is Power: A Critical Survey of “Bias” in NLP , 2020, ACL.

[6]  Nicholas Asher.  Evaluating conversational success: Weighted Message Exchange Games , 2019 .

[7]  Soumya Paul,et al.  Conversation and Games , 2017, ICLA.

[8]  Nat Hansen,et al.  Literal Meaning: Introduction , 2003 .

[9]  D. Blackwell.  An analog of the minimax theorem for vector payoffs. , 1956 .

[10]  Pascal Denis,et al.  Expressivity and comparison of models of discourse structure , 2013, SIGDIAL Conference.

[11]  Ronald P. A. Petrick,et al.  Planning for Social Interaction with Sensor Uncertainty , 2014 .

[12]  Magdalena D. Bugajska,et al.  Building a Multimodal Human-Robot Interface , 2001, IEEE Intell. Syst..

[13]  R. Aumann.  Agreeing to disagree. , 1976, Nature cell biology.

[14]  Ani Nenkova,et al.  Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , 2016, NAACL 2016.

[15]  Christophe Marsala,et al.  Unjustified Classification Regions and Counterfactual Explanations in Machine Learning , 2019, ECML/PKDD.

[16]  Eric Horvitz,et al.  Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration , 2016, AAAI.

[17]  Justin Khoo,et al.  Code Words in Political Discourse , 2017 .

[18]  I. Erev,et al.  Simultaneous Over- and Underconfidence: The Role of Error in Judgment Processes. , 1994 .

[19]  Anthony Hunter,et al.  Elements of Argumentation , 2007, ECSQARU.

[20]  David Lewis.  Convention: A Philosophical Study , 1986 .

[21]  J. Greenstone.  Relevance , 2007 .

[22]  Dirk Ifenthaler,et al.  Stochastic Models of Learning , 2012 .

[23]  N. Solomon,et al.  Unreliable Sources: A Guide to Detecting Bias in News Media , 1990 .

[24]  Faruk Gul,et al.  SELF-CONTROL AND THE THEORY OF CONSUMPTION , 1999 .

[25]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[26]  Matthew Stone,et al.  Imagination and Convention: Distinguishing Grammar and Inference in Language , 2014 .

[27]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[28]  Michael P. Wellman,et al.  Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm , 1998, ICML.

[29]  Michael L. Littman,et al.  Markov Games as a Framework for Multi-Agent Reinforcement Learning , 1994, ICML.

[30]  N. Wilkinson,et al.  An Introduction to Behavioral Economics , 2007 .

[31]  David H. Wolpert,et al.  The Lack of A Priori Distinctions Between Learning Algorithms , 1996, Neural Computation.

[32]  J. Banks,et al.  Switching Costs and the Gittins Index , 1994 .

[33]  Prashant Parikh,et al.  Communication and strategic inference , 1991 .

[34]  Jerry R. Hobbs,et al.  Interpretation as Abduction , 1993, Artif. Intell..

[35]  Aurélien Garivier,et al.  The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond , 2011, COLT.

[36]  J. Stanley.  How Propaganda Works , 2015 .

[37]  Alex Lascarides,et al.  Grounding Strategic Conversation: Using Negotiation Dialogues to Predict Trades in a Win-Lose Game , 2013, EMNLP.

[38]  J. Saul.  Dogwhistles, Political Manipulation, and Philosophy of Language , 2018, Oxford Scholarship Online.

[39]  Alex Lascarides,et al.  Logics of Conversation , 2005, Studies in natural language processing.

[40]  Jason Konek.  Probabilistic Knowledge and Cognitive Ability , 2016 .

[41]  Tilman Börgers,et al.  Learning Through Reinforcement and Replicator Dynamics , 1997 .

[42]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[43]  Frederick Mosteller,et al.  Stochastic Models for Learning , 1956 .

[44]  Christopher Potts.  The logic of conventional implicatures , 2004 .

[45]  Soumya Paul,et al.  Strategic Conversations Under Imperfect Information: Epistemic Message Exchange Games , 2018, Journal of Logic, Language and Information.

[46]  A. Tversky,et al.  The framing of decisions and the psychology of choice. , 1981, Science.

[47]  Douglas L. Hintzman,et al.  MINERVA 2: A simulation model of human memory , 1984 .

[48]  Nicholas Asher,et al.  Integer Linear Programming for Discourse Parsing , 2016, NAACL.

[49]  A. Rubinstein,et al.  On Optimal Rules of Persuasion , 2004 .

[50]  H. Grice.  Utterer's meaning and intentions , 1969 .

[51]  Pierpaolo Battigalli,et al.  Rationalizability in infinite, dynamic games with incomplete information , 2003 .

[52]  J. Baron.  Thinking and Deciding , 2023 .

[53]  S. Moss.  Epistemology Formalized , 2012 .

[54]  Nicholas Asher,et al.  Reference to abstract objects in discourse , 1993, Studies in linguistics and philosophy.

[55]  Apostolos Burnetas,et al.  Optimal Adaptive Policies for Markov Decision Processes , 1997, Math. Oper. Res..

[56]  Alex Lascarides,et al.  Commitments to Preferences in Dialogue , 2011, SIGDIAL Conference.

[57]  P. Whittle.  Multi‐Armed Bandits and the Gittins Index , 1980 .

[58]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[59]  A. Tversky,et al.  Extensional versus intuitive reasoning: the conjunction fallacy in probability judgment , 1983 .

[60]  Prashant Parikh.  The use of language , 2001 .

[61]  Daniel Kahneman,et al.  Availability: A heuristic for judging frequency and probability , 1973 .

[62]  Robert van Rooy.  Signalling Games Select Horn Strategies , 2004 .

[63]  Ido Dagan,et al.  Semantic Similarity: What for? , 2006 .

[64]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[65]  Alex Lascarides,et al.  Strategic conversation , 2012 .

[66]  Robert van Rooy,et al.  SIGNALLING GAMES SELECT HORN STRATEGIES , 2004 .

[67]  Eric Horvitz,et al.  Discovering Blind Spots of Predictive Models: Representations and Policies for Guided Exploration , 2016, ArXiv.

[68]  Heather Burnett,et al.  Sociolinguistic interaction and identity construction: The view from game‐theoretic pragmatics , 2017 .

[69]  M. Hilbert,et al.  Toward a synthesis of cognitive biases: how noisy information processing can bias human decision making. , 2012, Psychological bulletin.

[70]  David I. Beaver,et al.  Toward a Non-Ideal Philosophy of Language , 2018 .

[71]  Conversations and Incomplete Knowledge , 2013 .

[72]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

[73]  Nicholas Asher,et al.  A Dependency Perspective on RST Discourse Parsing and Evaluation , 2018, CL.

[74]  Nathanael Chambers,et al.  A Dialogue-Based Approach to Multi-Robot Team Control , 2005 .

[75]  William C. Mann,et al.  Rhetorical Structure Theory: A Framework for the Analysis of Texts , 1987 .

[76]  R. Henderson,et al.  Dogwhistles and the At-Issue/Non-At-Issue Distinction , 2019, Secondary Content.

[77]  H. Robbins,et al.  Asymptotically efficient adaptive allocation rules , 1985 .

[78]  Marie-Jeanne Lesot,et al.  The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations , 2019, IJCAI.

[79]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[80]  H. Grice.  Logic and conversation , 1975 .

[81]  Soumya Paul,et al.  Message Exchange Games in Strategic Contexts , 2017, J. Philos. Log..

[82]  Douglas L. Hintzman,et al.  Judgments of frequency and recognition memory in a multiple-trace memory model. , 1988 .

[83]  John C. Harsanyi,et al.  Games with Incomplete Information Played by "Bayesian" Players, I-III: Part I. The Basic Model& , 2004, Manag. Sci..