Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction
This work provides an incremental improvement for researchers and practitioners working on relation extraction by enhancing existing models through a multi-task learning setup.
This paper proposes a multi-task learning approach to improve Relation Extraction (RE) by jointly training RE models with Knowledge Graph Link Prediction (KGLP) tasks. The method leverages the intertwined objectives of these two tasks, where a predicted relation from RE can be used by KGLP to predict objects, expecting the original object to be within the predicted set. The approach consistently improves the performance of several existing RE models.
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.