Distributional–relational database
A distributional–relational database, or word-vector database, is a
As distributional word-vectors can be built automatically from large-scale corpora,[1] this enrichment supports the construction of databases which can embed large-scale commonsense background knowledge into their operations. Distributional-Relational models can be applied to the construction of schema-agnostic databases (databases in which users can query the data without being aware of its schema), semantic search, schema-integration and inductive and abductive reasoning as well as different applications in which a semantically flexible knowledge representation model is needed. The main advantage of distributional–relational models over purely logical / semantic web models is the fact that the core semantic associations can be automatically captured from corpora, in contrast to the definition of manually curated ontologies and rule knowledge bases.[2]
Distributional–relational models
Distributional–relational models were first formalized,[3][4] as a mechanism to cope with the vocabulary/semantic gap between users and the schema behind the data. In this scenario, distributional semantic relatedness measures, combined with semantic pivoting heuristics can support the approximation between user queries (expressed in their own vocabulary), and data (expressed in the vocabulary of the designer).
In this model, the database symbols (entities and relations) are embedded into a distributional
References
- ^ Harris, Z. (1954). "Distributional structure". Word. 10 (23): 146–162.
- ISBN 978-3-319-07983-7.
- ^ Freitas, A. “Schema-agnostic queries over large-schema databases: a distributional semantics approach” PhD Thesis, 2015
- ^ Freitas, A., Handschuh, S., Curry, E., Distributional-Relational Models: Scalable Semantics for Databases, AAAI Spring Symposium, Knowledge Representation & Reasoning Track, Stanford, 2014