Duplicate Detection in a Knowledge Base with PIKA

Maxime Prieur, Guillaume Gadek, Bruno Grilheres

2022

Abstract

This paper explores the use of Graph Neural Network models producing node embeddings, in order to solve the not fully addressed problem of detecting similar items stored in a knowledge base. Leveraging pre-trained models for textual semantic similarity, our proposed method PIKA aggregates heterogeneous (structured and unstructured) characteristics of an entity and its neighborhood to produce an embedding vector that can be used in different tasks such as information retrieval or classification tasks. Our method learns specific weights for each information brought by an entity, enabling us to process it in an inductive fashion.

Paper Citation

in Harvard Style

Prieur M., Gadek G. and Grilheres B. (2022). Duplicate Detection in a Knowledge Base with PIKA. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-547-0, pages 46-54. DOI: 10.5220/0010769500003116

in Bibtex Style

@conference{icaart22,
author={Maxime Prieur and Guillaume Gadek and Bruno Grilheres},
title={Duplicate Detection in a Knowledge Base with PIKA},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2022},
pages={46-54},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010769500003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Duplicate Detection in a Knowledge Base with PIKA
SN - 978-989-758-547-0
AU - Prieur M.
AU - Gadek G.
AU - Grilheres B.
PY - 2022
SP - 46
EP - 54
DO - 10.5220/0010769500003116