The CoRg Project: Cognitive Reasoning

The term cognitive computing refers to new hardware and/or software that mimics the functioning of the human brain. In the context of question answering and commonsense reasoning this means that the reasoning process of humans shall be modeled by adequate technical means. However, since humans do not follow the rules of classical logic, a system designed to model these abilities must be very versatile. The aim of the CoRg project (Cognitive Reasoning) is to successfully complete a reasoning task with commonsense reasoning. We address different benchmarks with focus on the COPA benchmark set (Choice of Plausible Alternatives). Since humans naturally use background knowledge, we have to deal with large background knowledge bases and must be able to reason with multiple input formats and sources in the CoRg system, in order to draw explainable conclusions. For this, we have to find appropriate logics for cognitive reasoning. For a successful reasoning system, nowadays it seems to be important to combine automated reasoning with machine learning technology like recurrent neural networks.

[1]  Nathanael Chambers,et al.  LSDSem 2017 Shared Task: The Story Cloze Test , 2017, LSDSem@EACL.

[2]  Wolfgang Spohn,et al.  The Laws of Belief - Ranking Theory and Its Philosophical Applications , 2012 .

[3]  Elena Cabrio,et al.  KNEWS: Using Logical and Lexical Semantics to Extract Knowledge from Natural Language , 2016, ECAI 2016.

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

[5]  Claudia Schon,et al.  System Description: E-KRHyper 1.4 - Extensions for Unique Names and Description Logic , 2013, CADE.

[6]  Donald Nute,et al.  Defeasible Deontic Logic , 2010 .

[7]  Andrew S. Gordon,et al.  One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology , 2015, AAAI Spring Symposia.

[8]  Javier Álvez,et al.  Adimen-SUMO: Reengineering an Ontology for First-Order Reasoning , 2012, Int. J. Semantic Web Inf. Syst..

[9]  Ulrich Furbach,et al.  Commonsense Reasoning Meets Theorem Proving , 2016, Bridging@IJCAI.

[10]  P. Johnson-Laird,et al.  Causal reasoning with mental models , 2014, Front. Hum. Neurosci..

[11]  Seung-won Hwang,et al.  Commonsense Causal Reasoning between Short Texts , 2016, KR.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Zornitsa Kozareva,et al.  SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning , 2011, *SEMEVAL.

[14]  Frieder Stolzenburg,et al.  A series of revisions of David Poole’s specificity , 2016, Annals of Mathematics and Artificial Intelligence.

[15]  Ruth M. J. Byrne,et al.  ‘If’ and the problems of conditional reasoning , 2009, Trends in Cognitive Sciences.

[16]  Krysia Broda,et al.  Symbolic knowledge extraction from trained neural networks: A sound approach , 2001, Artif. Intell..

[17]  P. Johnson-Laird,et al.  Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness , 1985 .

[18]  Andrei Voronkov,et al.  Sine Qua Non for Large Theory Reasoning , 2011, CADE.

[19]  Simon Ostermann,et al.  SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge , 2018, *SEMEVAL.

[20]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[21]  Ulrich Furbach,et al.  The RatioLog Project: Rational Extensions of Logical Reasoning , 2015, KI - Künstliche Intelligenz.

[22]  Adam Pease,et al.  Towards a standard upper ontology , 2001, FOIS.

[23]  Douglas B. Lenat,et al.  CYC: a large-scale investment in knowledge infrastructure , 1995, CACM.

[24]  Gerhard Weikum,et al.  YAGO: A Large Ontology from Wikipedia and WordNet , 2008, J. Web Semant..

[25]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[26]  Xavier Parent,et al.  Deontic Logic and Normative Systems , 2014, Lecture Notes in Computer Science.

[27]  Fabrizio Cariani.  Deontic logic and normative systems : 12th international conference, DEON 2014, Ghent, Belgium, July 12-15, 2014 : proceedings , 2014 .

[28]  Frieder Stolzenburg,et al.  Commonsense Reasoning Using Theorem Proving and Machine Learning , 2019, CD-MAKE.