Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction

2020/12/09 by George Stoica, Stoica, George, Emmanouil Antonios Platanios +3
Computer Science · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2012.04812

openalex publication_date 2020/12/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O, given a subject and a relation from a knowledge graph. These two problems are closely related as their respective objectives are intertwined: given a sentence containing a subject and an object o, a RE model predicts a relation that can then be used by a KGLP model together with the subject, to predict a set of objects O. Thus, we expect object o to be in set O. In this paper, we leverage this insight by proposing a multi-task learning approach that improves the performance of RE models by jointly training on RE and KGLP tasks. We illustrate the generality of our approach by applying it on several existing RE models and empirically demonstrate how it helps them achieve consistent performance gains.

Citations

• Long Short-Term Memory
• Attention Guided Graph Convolutional Networks for Relation Extraction

Related

• KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction
• Relation Adversarial Network for Low Resource Knowledge Graph Completion
• RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
• Connecting Language and Knowledge with Heterogeneous Representations for Neural Relation Extraction
• Relations Prediction for Knowledge Graph Completion using Large Language Models