A Two-Phase Paradigm for Joint Entity-Relation Extraction

TL;DR

This paper introduces a two-phase span-based model for joint entity-relation extraction that reduces data imbalance issues and incorporates global features, achieving state-of-the-art results.

Contribution

The paper proposes a novel two-phase paradigm and combines entity type and distance features, improving span-based joint extraction performance.

Findings

Outperforms previous span-based models on multiple datasets

Reduces data imbalance between positive and negative samples

Establishes new benchmark for joint entity-relation extraction

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 spanbased 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.