Span-based joint entity and relation extraction augmented with sequence tagging mechanism

TL;DR

This paper introduces STSN, a novel span-based joint extraction model that integrates token-level label information through sequence tagging, significantly improving NER and RE performance on benchmark datasets.

Contribution

The paper proposes a new span-based joint extraction model with sequence tagging augmentation, enabling token-level label utilization and bi-directional NER and RE interaction.

Findings

STSN outperforms existing models on three benchmark datasets.

Achieves new state-of-the-art F1 scores in joint entity and relation extraction.

Demonstrates the effectiveness of token-level label integration in span-based models.

Abstract

Span-based joint extraction simultaneously conducts named entity recognition (NER) and relation extraction (RE) in text span form. However, since previous span-based models rely on span-level classifications, they cannot benefit from token-level label information, which has been proven advantageous for the task. In this paper, we propose a Sequence Tagging augmented Span-based Network (STSN), a span-based joint model that can make use of token-level label information. In STSN, we construct a core neural architecture by deep stacking multiple attention layers, each of which consists of three basic attention units. On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE. Experimental results on three benchmark datasets show that STSN consistently outperforms the strongest baselines in terms of F1, creating new state-of-the-art results.