Semantics-driven Keyword Search over Knowledge Graphs – L.Feddoul

Описание: Presented at the Doctoral Consortium at the 19th International Semantic Web Conference (ISWC2020)(https://iswc2020.semanticweb.org/) by Leila Feddoul (https://fusion.cs.uni-jena.de/fusion/....

Paper: Leila Feddoul. " Semantics-driven Keyword Search over Knowledge Graphs ". In 19th International Semantic Web Conference 2020 (ISWC’20), Doctoral Consortium.

Abstract:
With the continuous growth of data represented as knowledge graphs, advanced access techniques are in great demand. Keyword search is a convenient and simple method to retrieve information. It can be used as an alternative to structured query languages, since it does not require technical expertise. In the context of knowledge graphs, keyword search aims to find candidate subgraphs that connect the query keywords and thus answer user queries. Efficiently finding candidates and ranking them effectively is still a challenging task. The goal of this work is to automatically find appropriate subgraphs. The focus is particularly on enhancing the accuracy of subgraph ranking by leveraging semantic information combined with other factors. Preliminary results demonstrate that the combination of importance-based and semantics based metrics is promising compared to purely structural techniques.