Pathfinder associative networks: studies in knowledge organization
Pathfinder associative networks: studies in knowledge organization
Foundations of statistical natural language processing
Foundations of statistical natural language processing
Latent semantic indexing: a probabilistic analysis
Journal of Computer and System Sciences - Special issue on the seventeenth ACM SIGACT-SIGMOD-SIGART symposium on principles of database systems
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Visualisation Techniques for Analysing Meaning
TSD '02 Proceedings of the 5th International Conference on Text, Speech and Dialogue
Automatic word sense discrimination
Computational Linguistics - Special issue on word sense disambiguation
The Geometry of Information Retrieval
The Geometry of Information Retrieval
Geometry and Meaning
Methodological Review: Empirical distributional semantics: Methods and biomedical applications
Journal of Biomedical Informatics
Quantum latent semantic analysis
ICTIR'11 Proceedings of the Third international conference on Advances in information retrieval theory
CICLing'10 Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing
Hi-index | 0.01 |
This paper applies some recent methods involving semantic vectors and their combination operations to some very traditional questions, including the discovery of similarities and differences between the four Gospels, relationships between individuals, and the identification of geopolitical regions and leaders in the ancient world. In the process, we employ several methods from linear algebra and vector space models, some of which are of particular importance in quantum mechanics and quantum logic. Our conclusions are in general positive: the vector methods do a good job of capturing well-known facts about the Bible, its authors, and relationships between people and places mentioned in the Bible. On the more specific topic of quantum as opposed to other approaches, our conclusions are more mixed: on the whole, we do not find evidence for preferring vector methods that are directly associated with quantum mechanics over vector methods developed independently of quantum mechanics. We suggest that this argues for synthesis rather than division between classical and quantum models for information processing.