FUSION
FUnctionality Sharing In Open eNvironments
Heinz Nixdorf Chair for Distributed Information Systems
 

Semantics-driven Keyword Search over Knowledge Graphs

Title: Semantics-driven Keyword Search over Knowledge Graphs
Authors: Leila Feddoul
Source: 19th International Semantic Web Conference (ISWC2020)
Place: Virtual conference
Date: 2020-11-02
Type: Conference Paper
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.