QART: A Framework to Transform Natural Language Questions and Answers into RDF Triples

André Gomes Regino, Rodrigo Oliveira Caus, Victor Hochgreb, Julio Cesar Dos Reis

2022

Abstract

Knowledge Graphs (KGs) model real-world things and their interactions. Several software systems have recently adopted the use of KGs to improve their data handling. E-commerce platforms are examples of software exploring the power of KGs in diversified tasks, such as advertisement and product recommendation. In this context, generating trustful, meaningful and scalable RDF triples for populating KGs remains an arduous and error-prone task. The automatic insertion of new knowledge in e-commerce KGs is highly dependent on data quality, which is often not available. In this article, we propose a framework for generating RDF triple knowledge from natural language texts. The QART framework is suited to extract knowledge from Q&A regarding e-commerce products and generate triples associated with it. QART produces KG triples reliable to answer similar questions in an e-commerce context. We evaluate one of the key steps in QART to generate summary sentences and identify product Q&A intents and entities using templates. Our research results reveal the major challenges faced in building and deploying our framework. Our contribution paves the way for the development of automatic mechanisms for text-to-triple transformation in e-commerce systems.

Paper Citation

in Harvard Style

Regino A., Caus R., Hochgreb V. and Reis J. (2022). QART: A Framework to Transform Natural Language Questions and Answers into RDF Triples. In Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 2: KEOD; ISBN 978-989-758-614-9, SciTePress, pages 55-65. DOI: 10.5220/0011529200003335

in Bibtex Style

@conference{keod22,
author={André Gomes Regino and Rodrigo Oliveira Caus and Victor Hochgreb and Julio Cesar Dos Reis},
title={QART: A Framework to Transform Natural Language Questions and Answers into RDF Triples},
booktitle={Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 2: KEOD},
year={2022},
pages={55-65},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011529200003335},
isbn={978-989-758-614-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 2: KEOD
TI - QART: A Framework to Transform Natural Language Questions and Answers into RDF Triples
SN - 978-989-758-614-9
AU - Regino A.
AU - Caus R.
AU - Hochgreb V.
AU - Reis J.
PY - 2022
SP - 55
EP - 65
DO - 10.5220/0011529200003335
PB - SciTePress