FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction

TL;DR

This paper introduces FSUIE, a novel framework for universal information extraction that employs fuzzy span mechanisms to improve robustness, convergence speed, and performance across various IE tasks.

Contribution

The paper proposes fuzzy span loss and fuzzy span attention to address limitations of existing UIE models, enhancing their robustness and generalization capabilities.

Findings

Significant performance improvements over baselines.

Faster convergence with less data and fewer training epochs.

Effective across multiple IE tasks and scenarios.

Abstract

Universal Information Extraction (UIE) has been introduced as a unified framework for various Information Extraction (IE) tasks and has achieved widespread success. Despite this, UIE models have limitations. For example, they rely heavily on span boundaries in the data during training, which does not reflect the reality of span annotation challenges. Slight adjustments to positions can also meet requirements. Additionally, UIE models lack attention to the limited span length feature in IE. To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework. Specifically, our contribution consists of two concepts: fuzzy span loss and fuzzy span attention. Our experimental results on a series of main IE tasks show significant improvement compared to the baseline, especially in terms of fast convergence and strong performance with small amounts of data and training epochs. These results demonstrate the effectiveness and generalization of FSUIE in different tasks, settings, and scenarios.