Open AccessA semantic search approach for hyper relational knowledge graphs
Author(s) -
Veronica dos Santos,
Sérgio Lifschitz
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/sbbd_estendido.2021.18171
Subject(s) - computer science , semantic search , information retrieval , semantic matching , semantic similarity , vocabulary , set (abstract data type) , terminology , ambiguity , natural language , matching (statistics) , context (archaeology) , artificial intelligence , natural language processing , search engine , mathematics , paleontology , linguistics , statistics , philosophy , biology , programming language
Information Retrieval Systems usually employ syntactic search techniques to match a set of keywords with the indexed content to retrieve results. But pure keyword-based matching lacks on capturing user's search intention and context and suffers of natural language ambiguity and vocabulary mismatch. Considering this scenario, the hypothesis raised is that the use of embeddings in a semantic search approach will make search results more meaningfully. Embeddings allow to minimize problems arising from terminology and context mismatch. This work proposes a semantic similarity function to support semantic search based on hyper relational knowledge graphs. This function uses embeddings in order to find the most similar nodes that satisfy a user query.