Enriching Relation Extraction with OpenIE

Alessandro Temperoni, Maria Biryukov, Martin Theobald

2023

Abstract

Relation extraction (RE) is a sub-discipline of information extraction (IE) which focuses on the prediction of a relational predicate from a natural-language input unit. Together with named-entity recognition (NER) and disambiguation (NED), RE forms the basis for many advanced IE tasks such as knowledge-base (KB) population and verification. In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE by encoding structured information about the sentences’ principal units, such as subjects, objects, verbal phrases, and adverbials, into various forms of vectorized (and hence unstructured) representations of the sentences. Our main conjecture is that the decomposition of long and possibly convoluted sentences into multiple smaller clauses via OpenIE even helps to fine-tune context-sensitive language models such as BERT (and its plethora of variants) for RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models compared to existing RE approaches. Our best results reach 92% and 71% of F1 score for KnowledgeNet and FewRel, respectively, proving the effectiveness of our approach on competitive benchmarks.

Paper Citation

in Harvard Style

Temperoni A., Biryukov M. and Theobald M. (2023). Enriching Relation Extraction with OpenIE. In Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-664-4, SciTePress, pages 359-366. DOI: 10.5220/0012086100003541

in Bibtex Style

@conference{data23,
author={Alessandro Temperoni and Maria Biryukov and Martin Theobald},
title={Enriching Relation Extraction with OpenIE},
booktitle={Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2023},
pages={359-366},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012086100003541},
isbn={978-989-758-664-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Enriching Relation Extraction with OpenIE
SN - 978-989-758-664-4
AU - Temperoni A.
AU - Biryukov M.
AU - Theobald M.
PY - 2023
SP - 359
EP - 366
DO - 10.5220/0012086100003541
PB - SciTePress