Topological properties and organizing principles of semantic networks
This work provides foundational insights into semantic network structures, which is important for improving NLP applications, but it is incremental as it builds on existing network analysis without introducing new methods.
The study analyzed semantic networks from ConceptNet across 11 languages and found they are sparse, highly clustered, and often scale-free with power-law degree distributions, while some languages show deviations due to grammatical rules. It demonstrated that understanding similarity and complementarity in these networks can enhance NLP algorithms for missing link inference.
Interpreting natural language is an increasingly important task in computer algorithms due to the growing availability of unstructured textual data. Natural Language Processing (NLP) applications rely on semantic networks for structured knowledge representation. The fundamental properties of semantic networks must be taken into account when designing NLP algorithms, yet they remain to be structurally investigated. We study the properties of semantic networks from ConceptNet, defined by 7 semantic relations from 11 different languages. We find that semantic networks have universal basic properties: they are sparse, highly clustered, and many exhibit power-law degree distributions. Our findings show that the majority of the considered networks are scale-free. Some networks exhibit language-specific properties determined by grammatical rules, for example networks from highly inflected languages, such as e.g. Latin, German, French and Spanish, show peaks in the degree distribution that deviate from a power law. We find that depending on the semantic relation type and the language, the link formation in semantic networks is guided by different principles. In some networks the connections are similarity-based, while in others the connections are more complementarity-based. Finally, we demonstrate how knowledge of similarity and complementarity in semantic networks can improve NLP algorithms in missing link inference.