FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction
This work addresses span annotation challenges in information extraction for NLP researchers, but it is incremental as it builds on existing UIE frameworks.
The paper tackles the limitations of Universal Information Extraction (UIE) models, such as rigid span boundaries and lack of attention to span length, by proposing the FSUIE framework with fuzzy span loss and attention, resulting in significant improvements in fast convergence and performance with small data and training epochs.
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.