A Marker Passing Approach to Winograd Schemas

This paper approaches a solution of Winograd Schemas with a marker passing algorithm which operates on an automatically generated semantic graph. The semantic graph contains common sense facts from data sources form the semantic web like domain ontologies e.g. from Linked Open Data (LOD), WordNet, Wikidata, and ConceptNet. Out of those facts, a semantic decomposition algorithm selects relevant facts for the concepts used in the Winograd Schema and adds them to the semantic graph. Markers are propagated through the graph and used to identify an answer to the Winograd Schema. Depending on the encoded knowledge in the graph (connectionist view of world knowledge) and the information encoded on the marker (for symbolic reasoning) our approach selects the answers. With this selection, the marker passing approach is able to beat the state-of-the-art approach by about 12%.

[1]  Liuqing Yang,et al.  Where does AlphaGo go: from church-turing thesis to AlphaGo thesis and beyond , 2016, IEEE/CAA Journal of Automatica Sinica.

[2]  Joost C. F. de Winter,et al.  Why the Fitts list has persisted throughout the history of function allocation , 2011, Cognition, Technology & Work.

[3]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[4]  Anthony G. Cohn,et al.  The Role of Pragmatics in Solving the Winograd Schema Challenge , 2017, COMMONSENSE.

[5]  Rafael Peñaloza,et al.  Similarity-based relaxed instance queries , 2015, J. Appl. Log..

[6]  Jackie Chi Kit Cheung,et al.  A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge , 2018, NAACL-HLT.

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

[8]  Yasunori Yamamoto,et al.  Semantic Graph Analysis for Federated LOD Surfing in Life Sciences , 2017, JIST.

[9]  Jon A. Willits,et al.  11 Models of Semantic Memory , 2015 .

[10]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[11]  Roman V. Yampolskiy,et al.  AI-Complete, AI-Hard, or AI-Easy - Classification of Problems in AI , 2012, MAICS.

[12]  Leora Morgenstern,et al.  The First Winograd Schema Challenge at IJCAI-16 , 2017, AI Mag..

[13]  Raymond C. Kurzweil,et al.  The Singularity Is Near , 2018, The Infinite Desire for Growth.

[14]  Michael Pace-Sigge,et al.  Spreading Activation, Lexical Priming and the Semantic Web , 2018 .

[15]  Chitta Baral,et al.  Towards Addressing the Winograd Schema Challenge - Building and Using a Semantic Parser and a Knowledge Hunting Module , 2015, IJCAI.

[16]  John R. Searle,et al.  Minds, brains, and programs , 1980, Behavioral and Brain Sciences.

[17]  M. Ross Quillian,et al.  Retrieval time from semantic memory , 1969 .

[18]  J. H. Neely.  Semantic priming and retrieval from lexical memory: Roles of inhibitionless spreading activation and limited-capacity attention. , 1977 .

[19]  Vincent Ng,et al.  Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge , 2012, EMNLP.

[20]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[21]  Jon A. Willits,et al.  Models of Semantic Memory , 2015 .

[22]  Lance J. Rips,et al.  Structure and process in semantic memory: A featural model for semantic decisions. , 1974 .

[23]  Sebastian Ahrndt,et al.  Design and Use of a Semantic Similarity Measure for Interoperability Among Agents , 2016, MATES.

[24]  Yu Hu,et al.  Combing Context and Commonsense Knowledge Through Neural Networks for Solving Winograd Schema Problems , 2017, AAAI Spring Symposia.

[25]  Fabio Crestani,et al.  Application of Spreading Activation Techniques in Information Retrieval , 1997, Artificial Intelligence Review.

[26]  Evgeny Kharlamov,et al.  Faceted search over RDF-based knowledge graphs , 2016, J. Web Semant..

[27]  Leora Morgenstern,et al.  Planning, Executing, and Evaluating the Winograd Schema Challenge , 2016, AI Mag..

[28]  Jim Austin,et al.  Distributed associative memories for high-speed symbolic reasoning , 1996, Fuzzy Sets Syst..

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

[30]  R. Sun.  A Connectionist Model for Commonsense Reasoning Incorporating Rules and Similarities , 1992 .

[31]  Dan Roth,et al.  Solving Hard Coreference Problems , 2019, NAACL.

[32]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[33]  Freddy Lécué.  Applying Machine Reasoning and Learning in Real World Applications , 2016, Reasoning Web.

[34]  Paolo Traverso,et al.  The actor's view of automated planning and acting: A position paper , 2014, Artif. Intell..