Print Email Facebook Twitter Topological Properties of Semantic Networks Title Topological Properties of Semantic Networks Author Jin, Ying (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Kooij, Robert (mentor) Kitsak, M.A. (graduation committee) Dubbeldam, J.L.A. (graduation committee) Degree granting institution Delft University of Technology Programme Electrical Engineering | Wireless Communication and Sensing Date 2022-09-29 Abstract The main goal of this thesis is to understand the topological properties of semantic networks, to find language-specific patterns, and to investigate their connection principles. Interpreting unstructured texts in natural language is a crucial task for computers. Natural Language Processing (NLP) applications rely on semantic networks for structured knowledge representation. Although NLP technologies have been applied to various domains with some degree of success, they still face many challenges due to the ambiguity of human language. To inform better algorithms, we need to pay attention to fundamental structures of semantic networks in different languages. However, these remain to be investigated properly. In this thesis we extract semantic networks with 7 distinct relations for 11 languages from ConceptNet. We systematically analyze the degree distribution, degree correlation and clustering of these networks. We also measure their structural similarity and complementarity coefficients. Our findings show that semantic networks have universalities in basic structures: they have high sparsity, high clustering, and power-law degree distributions. Our findings also show that the majority of the considered networks are scale-free. In addition, our results show that networks in different languages exhibit different properties, which are determined by grammatical rules. For example, the networks of highly inflected languages show peaks in the degree distributions that deviate from a power-law. Furthermore, we find that depending on the type of semantic relation and the language, the connection principles of networks are different. Some networks are more similarity-based, while others are more complementarity-based. We conclude the thesis by demonstrating how the knowledge of similarity and complementarity can better inform NLP in link prediction tasks. Subject Semantic NetworksTopological PropertiesSemantic AnalysisGraph TheorySimilarityComplementarity To reference this document use: http://resolver.tudelft.nl/uuid:fa88ab71-0825-4bb8-8d3c-b22a451b2c45 Part of collection Student theses Document type master thesis Rights © 2022 Ying Jin Files PDF Master_Thesis_Semantic_Ne ... ing_v2.pdf 3.06 MB Close viewer /islandora/object/uuid:fa88ab71-0825-4bb8-8d3c-b22a451b2c45/datastream/OBJ/view