Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation
This addresses the challenge of limited labeled data for entity and relation extraction, showing incremental improvement by jointly handling both tasks in a semi-supervised manner.
The paper tackled the problem of extracting entities and relations from limited data by proposing Jointprop, a joint semi-supervised learning framework using heterogeneous graph-based propagation, which outperformed state-of-the-art methods on benchmark datasets for NER and RE tasks.
Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data.