Researchers at the University of Southern California have embarked on an ambitious project to explore the commonsense models that people have of their own reasoning processes, commonsense psychology. Commonsense psychology has been studied by many researchers across a number of fields in the past, sometimes under the heading of Naive Psychology, Theory of Mind, and Social Cognition.

Our efforts at USC have focused in four areas. First, we have defined the representational scope of commonsense psychology through a large scale analysis of planning strategies. Second, we have formalized commonsense psychology concepts into axiomatic, predicate calculus theories. Third, we have identified all of the English words and phrases that are used to refer to concepts in commonsense psychology, and encoded them as local grammars. Fourth, we have specified a cognitive architecture based on commonsense psychology that integrates heterogenous cognitive models under a common framework.

These first of these efforts has been described in a number of published reports, particularly the following:

• Gordon, Andrew S. (2002) The Theory of Mind in Strategy Representations. Proceedings of the Twenty-fourth Annual Meeting of the Cognitive Science Society (CogSci-2002), George Mason University, Aug 7-10. Mahwah, NJ: Lawrence Erlbaum Associates. pdf

2. Logic

In the tradition of formal knowledge representation, researchers at USC have begun the authoring of a large collection of integrated theories that each describe components of our commonsense psychological models. To aid in reusability, these theories are being authored as standard predicate calculus theories, and will be made available in various knowledge interchange formats.

• Hobbs, J. & Gordon, A. (2008) The Deep Lexical Semantics of Emotions. Workshop on Sentiment Analysis: Emotion, Metaphor, Ontology and Terminology (EMOT-08), 6th International conference on Language Resources and Evaluation (LREC-08), Marrakech, Morocco, May 27, 2008. pdf
• Hobbs, Jerry & Gordon, Andrew (2005) Encoding Knowledge of Commonsense Psychology. 7th International Symposium on Logical Formalizations of Commonsense Reasoning. May 22-24, 2005, Corfu, Greece. pdf
• Hobbs, Jerry & Gordon, Andrew (2005) Toward a Large-Scale Formal Theory of Commonsense Psychology for Metacognition. 2005 AAAI Spring Symposium on Metacognitive Computing. March 21-23, Stanford, CA. pdf
• Swanson, Reid & Gordon, Andrew (2005) Automated Commonsense Reasoning About Human Memory. 2005 AAAI Spring Symposium on Metacognitive Computing. March 21-23, Stanford, CA. pdf
• Gordon, Andrew S. & Hobbs, Jerry R. (2004) Formalizations of Commonsense Psychology. AI Magazine 25(4):49-62. pdf
• Gordon, Andrew S. and Hobbs, Jerry R. (2003) Coverage and Competency in Formal Theories: A Commonsense Theory of Memory. Proceedings of the 2003 AAAI Spring Symposium on Logical Formalizations of Commonsense Reasoning, Stanford University, March 24-26, 2003. pdf

3. Language

In an effort to better understand the relationship between language and representation, we have authored a lexical-semantic resource for identifying reference to commonsense psychology concepts in English text. This resource was authored as a set of local grammars, encoded as finite-state transducers, that can be applied to large text corpora for concept-level tagging & markup. This resource was authored using the Intex NLP development environment authored by Max Silberztein, originally at the LADL, University of Paris 7, and now at the GRELIS/LASELDI, Universite de Franche-Comte, France. These local grammars are constructed on top of a large-coverage dictionary of English words compiled by Blandine Courtois.

Our group completed finite-state transducers for the 30 representational areas of Commonsense Psychology that were identified through strategy representation. A total of 529 concept tags are used in these transducers. Provided here are the graphs associated with each of these representational areas, in the original Intex graph format.

These resources have been applied in a number of different language analysis projects, and have been evaluated to determine their precision and recall performance. The following reports are available:

• Gordon, Andrew S. (2006) Language evidence for changes in a Theory of Mind. In M. Arbib (ed) Action to Language via the Mirror Neuron System. Cambridge, UK: Cambridge University Press. info
• Gordon, Andrew S. & Nair, Anish (2004) Expressions Related to Knowledge and Belief in Children's Speech. Proceedings of the 26th Annual Meeting of the Cognitive Science Society (CogSci-2004), August 5-7, Chicago. Mahwah, NJ: Lawrence Erlbaum Associates. pdf
• Gordon, Andrew, Kazemzadeh, Abe, Nair, Anish, and Petrova, Milena (2003) Recognizing Expressions of Commonsense Psychology in English Text. Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-2003) Sapporo, Japan, July 7-12, 2003. pdf
• Gordon, Andrew and Nair, Anish (2003) Literary Evidence for the Cultural Development of a Theory of Mind. Proceedings of the 25th Annual Meeting of the Cognitive Science Society (CogSci-03). July 31-Aug 2, Boston, MA. pdf

4. Cognitive models

One of the specific aims of this research program is to support the devleopment of integrative cognitive models of human cognition. We believe that our commonsense psychological models can serve as an important integrator of existing computational models of different reasoning modules, including planning, scheduling, memory retrieval, similarity judgements, belief revision, explanation, prediction, among others. The following papers are available:

• Gordon, A., Hobbs, J. & Cox, M. (2008) Anthropomorphic self-models for metareasoning agents. AAAI Workshop on Metareasoning: Thinking about thinking. July 13-14, 2008, Chicago, IL. pdf
• Gordon, Andrew S. (2005) Commonsense Psychology and the Functional Requirements of Cognitive Models. Proceedings of the 2005 AAAI Workshop on Modular Construction of Human-like Intelligence, July 10, 2005, Pittsburgh, PA. Menlo Park, CA: AAAI Press. pdf

5. Project team

The principle investigators for this research effort are Andrew S. Gordon (gordon@ict.usc.edu) of the USC Institute for Creative Technologies and Jerry R. Hobbs of the USC Information Sciences Institute (hobbs@isi.edu). Current and past team members include USC students, namely Abe Kazemzadeh, Milena Petrova, Anish Nair, Jeen Jeong, Reid Swanson, Ryan Kashfian, Ashish Mestry, and Rachana Pandya.