Open Access

ARTICLE

A Two-Phase Paradigm for Joint Entity-Relation Extraction

Bin Ji¹, Hao Xu¹, Jie Yu¹, Shasha Li¹, Jun Ma¹, Yuke Ji^2,*, Huijun Liu¹
1 College of Computer, National University of Defense Technology, Changsha, 410073, China
2 The Affiliated Eye Hospital of Nanjing Medical University, Nanjing, 210029, China
* Corresponding Author: Yuke Ji. Email:

Computers, Materials & Continua 2023, 74(1), 1303-1318. https://doi.org/10.32604/cmc.2023.032168

Received 09 May 2022; Accepted 12 June 2022; Issue published 22 September 2022

Abstract

An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction task. However, these models sample a large number of negative entities and negative relations during the model training, which are essential but result in grossly imbalanced data distributions and in turn cause suboptimal model performance. In order to address the above issues, we propose a two-phase paradigm for the span-based joint entity and relation extraction, which involves classifying the entities and relations in the first phase, and predicting the types of these entities and relations in the second phase. The two-phase paradigm enables our model to significantly reduce the data distribution gap, including the gap between negative entities and other entities, as well as the gap between negative relations and other relations. In addition, we make the first attempt at combining entity type and entity distance as global features, which has proven effective, especially for the relation extraction. Experimental results on several datasets demonstrate that the span-based joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-of-the-art span-based models for the joint extraction task, establishing a new standard benchmark. Qualitative and quantitative analyses further validate the effectiveness the proposed paradigm and the global features.

---

Keywords

Joint extraction; span-based; named entity recognition; relation extraction; data distribution; global features

---