TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks

Anonymous

TL;DR: A true UIE method which first unified all IE tasks into one common task.

Abstract: Information extraction (IE) encounters challenges due to the variety of schemas and objectives that differ across tasks. Recent advancements hint at the potential for universal approaches to model such tasks, referred to as Universal Information Extraction (UIE). While handling diverse tasks in one model, their generalization is limited since they are actually learning task-specific knowledge. In this study, we introduce an innovative paradigm known as TRUE-UIE, wherein all IE tasks are aligned to learn the same goals: extracting mention spans and two universal relations named NEXT and IS. During the decoding process, the NEXT relation is utilized to group related elements, while theIS relation, in conjunction with structured language prompts, undertakes the role of type recognition. Additionally, we consider the sequential dependency of tokens during span extraction, an aspect often overlooked in prevalent models. Our empirical experiments indicate that TRUE-UIE achieves state-of-the-art performance on established benchmarks encompassing 16 datasets, spanning 7 diverse IE tasks.

Paper Type: long

Research Area: Information Extraction

Contribution Types: Approaches to low-resource settings

Languages Studied: English, Chinese