Enhancing Keyword Search in Relational Databases with Word Embeddings | Zendy

Fatemeh Khalifeh | Zendy; Mohammad Taheri | Zendy; Eghbal Mansoori | Zendy; Mostafa Fakhrahmad | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Enhancing Keyword Search in Relational Databases with Word Embeddings

Author(s) -

Fatemeh Khalifeh,

Mohammad Taheri,

Eghbal Mansoori,

Mostafa Fakhrahmad

Publication year - 2025

Publication title -

ieee access

Language(s) - English

Resource type - Magazines

SCImago Journal Rank - 0.587

H-Index - 127

eISSN - 2169-3536

DOI - 10.1109/access.2025.3574428

Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation

Keyword search in relational databases allows the users to query these databases using natural language keywords, bridging the gap between structured data and intuitive querying. However, ambiguity in user queries as well as the complexities of structured database relationships often complicate the retrieval of relevant results. This paper introduces Key2Vec as a framework for leveraging the Natural Language Processing (NLP) techniques, specifically Word2Vec embeddings, for enhancing the keyword search in relational databases. Key2Vec enhances both the query relevance and the execution efficiency by semantically interpreting the keywords and optimizing the query classes, those categories of user queries which are grouped by their specific objectives and their data requirements. Experimental evaluations, on benchmark databases, demonstrate that Key2Vec improves the accuracy about 25% and reduces the query processing time by 30%, establishing it as a robust solution.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Empowering knowledge with every search