Conceptual Modeling with Formal Concept Analysis on Natural Language Texts

The paper presents conceptual modelling technique on natural language texts. This technique combines the usage of two conceptual modeling paradigms: conceptual graphs and Formal Concept Analysis. Conceptual graphs serve as semantic models of text sentences and the data source for concept lattice – the basic conceptual model in Formal Concept Analysis. With the use of conceptual graphs the Text Mining problems of Named Entity Recognition and Relations Extraction are solved. Then these solutions are applied for creating concept lattice. The main problem investigated in the paper is the problem of creating formal contexts on a set of conceptual graphs. Its solution is based on the analysis of semantic roles and conceptual patterns in conceptual graphs. Concept lattice built on textual data is applied for knowledge extraction. Knowledge, sometimes interpreted as facts, can be extracted by using navigation in the lattice and interpretation its concepts and hierarchical links between them. Experimental investigation of the proposed technique is performed on the annotated textual corpus consisted of descriptions of biotopes of bacteria. †The paper concerns the work which is partially supported by Russian Foundation of Basic Research, grant No 15-07-05507