Topological properties and organizing principles of semantic networks

by   Gabriel Budel, et al.

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 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.


page 1

page 10


Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery

Text-based representations of chemicals and proteins can be thought of a...

Predicting the Semantic Textual Similarity with Siamese CNN and LSTM

Semantic Textual Similarity (STS) is the basis of many applications in N...

Indian Language Wordnets and their Linkages with Princeton WordNet

Wordnets are rich lexico-semantic resources. Linked wordnets are extensi...

Architecture and evolution of semantic networks in mathematics texts

Knowledge is a network of interconnected concepts. Yet, precisely how th...

Enhancing Networking Cipher Algorithms with Natural Language

This work provides a survey of several networking cipher algorithms and ...

Semantic Folding Theory And its Application in Semantic Fingerprinting

Human language is recognized as a very complex domain since decades. No ...

Language Invariant Properties in Natural Language Processing

Meaning is context-dependent, but many properties of language (should) r...

Please sign up or login with your details

Forgot password? Click here to reset