We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis. Our approach converts the text-based IE tasks as the token-pair problem, which uniformly disassembles all extraction targets into joint span detection, classification and association problems with a unified extractive framework, namely UniEX. UniEX can synchronously encode schema-based prompt and textual information, and collaboratively learn the generalized knowledge from pre-defined information using the auto-encoder language models. We develop a traffine attention mechanism to integrate heterogeneous factors including tasks, labels and inside tokens, and obtain the extraction target via a scoring matrix. Experiment results show that UniEX can outperform generative universal IE models in terms of performance and inference-speed on 14 benchmarks IE datasets with the supervised setting. The state-of-the-art performance in low-resource scenarios also verifies the transferability and effectiveness of UniEX.
@article{arxiv.2305.10306,
title = {UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective},
author = {Ping Yang and Junyu Lu and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Jiaxing Zhang and Pingjian Zhang},
journal= {arXiv preprint arXiv:2305.10306},
year = {2023}
}