1,721,099 research outputs found
Perspectives of Neural-Symbolic Integration
No full textHammer B, Hitzler P, eds. Perspectives of Neural-Symbolic Integration. Studies in Computational Intelligence, 77. Berlin: Springer; 2007
The Core Method: Connectionist Model Generation for First-Order Logic Programs
No full textKnowledge based artificial networks networks have been applied quite successfully to propositional knowledge representation and reasoning tasks. However, as soon as these tasks are extended to structured objects and structure-sensitive processes it is not obvious at all how neural symbolic systems should look like such that they are truly connectionist and allow for a declarative reading at the same time. The core method aims at such an integration. It is a method for connectionist model generation using recurrent networks with feed-forward core. After an introduction to the core method, this paper will focus on possible connectionist representations of structured objects and their use in structure-sensitive reasoning tasks
M.: Querying formal contexts with answer set programs
Get PDFAbstract. Recent studies showed how a seamless integration of formal concept analysis (FCA), logic of domains, and answer set programming (ASP) can be achieved. Based on these results for combining hierarchical knowledge with classical rule-based formalisms, we introduce an expressive common-sense query language for formal contexts. Although this approach is conceptually based on order-theoretic paradigms, we show how it can be implemented on top of standard ASP systems. Advanced features, such as default negation and disjunctive rules, thus become practically available for processing contextual data.
Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
No full textThis chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are discussed. The situations in which this combination is most appropriate are characterized, including quantitative evaluation and qualitative error analysis on a variety of commonsense question answering benchmark datasets.</p
Query-Based Multicontexts for Knowledge Base Browsing: an Evaluation
Full text linkTane J, Cimiano P, Hitzler P. Query-Based Multicontexts for Knowledge Base Browsing: an Evaluation. In: Schärfe H, Hitzler P, Øhrstrøm P, eds. Conceptual Structures: Inspiration and Application: 14th International Conference on Conceptual Structures, ICCS 2006, Aalborg, Denmark, July 16-21, 2006. Proceedings. Lecture Notes in Computer Science, 4068. Springer; 2006: 413-426
DOLCE ergo SUMO: On Foundational and Domain Models in SWIntO (SmartWeb Integrated Ontology)
Full text linkOberle D, Ankolekar A, Hitzler P, et al. DOLCE ergo SUMO: On Foundational and Domain Models in SWIntO (SmartWeb Integrated Ontology). Journal of Web Semantics: Science, Services and Agents on the World Wide Web. 2007;5(3):156-174
Ontology Learning using corpus-derived Formal Contexts
No full textCimiano P. Ontology Learning using corpus-derived Formal Contexts. In: Hitzler P, Scharfe H, eds. Conceptual Structures in Practice. Chapman & Hall/CRC studies in informatics series. Boca Raton: Chapman & Hall/CRC Press; 2009: 199-222
Acquisition of OWL DL Axioms from Lexical Resources
Full text linkVölker J, Hitzler P, Cimiano P. Acquisition of OWL DL Axioms from Lexical Resources. In: Franconi E, Kifer M, May W, eds. The Semantic Web: Research and Applications, 4th European Semantic Web Conference, ESWC 2007, Innsbruck, Austria, June 3-7, 2007, Proceedings. Lecture Notes in Computer Science, 4519. Springer; 2007: 670-685
Type-elimination-based reasoning for the description logic SHIQbs using decision diagrams and disjunctive datalog
Get PDFWe propose a novel, type-elimination-based method for standard reasoning in the description logic SHIQbs extended by DL-safe rules. To this end, we first establish a knowledge compilation method converting the terminological part of an ALCIb knowledge base into an ordered binary decision diagram (OBDD) that represents a canonical model. This OBDD can in turn be transformed into disjunctive Datalog and merged with the assertional part of the knowledge base in order to perform combined reasoning. In order to leverage our technique for full SHIQbs, we provide a stepwise reduction from SHIQbs to ALCIb that preserves satisfiability and entailment of positive and negative ground facts. The proposed technique is shown to be worst-case optimal w.r.t. combined and data complexity. ©S. Rudolph, M. Krötzsch, and P. Hitzler
Perspectives and challenges for recurrent neural network training
No full textGori M, Hammer B, Hitzler P, Palm G. Perspectives and challenges for recurrent neural network training. Logic Journal of the IGPL. 2010;18(5):617-619
- …
