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.

翻译：我们提出了一种适用于任意模式格式且可应用于多种信息抽取任务（如命名实体识别、关系抽取、事件抽取和情感分析）的通用信息抽取新范式。该方法将基于文本的信息抽取任务转化为标记对问题，通过统一抽取框架UniEX将所有抽取目标分解为联合跨度检测、分类与关联问题。UniEX能够同步编码基于模式的提示信息和文本信息，并利用自编码语言模型从预定义信息中协作学习通用知识。我们设计了跨注意力机制来整合包含任务、标签及内部标记在内的异质因素，并通过评分矩阵获取抽取目标。实验结果表明，在监督设置下，UniEX在14个基准信息抽取数据集上的性能和推理速度均优于生成式通用信息抽取模型。其在低资源场景下的最优性能也验证了UniEX的可迁移性和有效性。