Leveraging Knowledge Graph Embeddings to Enhance Contextual Representations for Relation Extraction

• Published in: arXiv.org
• Main Authors: Laleye, Fréjus A A, Rakotoson, Loïc, Massip, Sylvain
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 07.06.2023
• Subjects: Computer Science - Computation and Language; Computer Science - Learning; Knowledge representation; Natural language processing; Performance enhancement
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2306.04203

Relation extraction task is a crucial and challenging aspect of Natural Language Processing. Several methods have surfaced as of late, exhibiting notable performance in addressing the task; however, most of these approaches rely on vast amounts of data from large-scale knowledge graphs or language models pretrained on voluminous corpora. In this paper, we hone in on the effective utilization of solely the knowledge supplied by a corpus to create a high-performing model. Our objective is to showcase that by leveraging the hierarchical structure and relational distribution of entities within a corpus without introducing external knowledge, a relation extraction model can achieve significantly enhanced performance. We therefore proposed a relation extraction approach based on the incorporation of pretrained knowledge graph embeddings at the corpus scale into the sentence-level contextual representation. We conducted a series of experiments which revealed promising and very interesting results for our proposed approach.The obtained results demonstrated an outperformance of our method compared to context-based relation extraction models.