arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09232cs.CL
收藏

Text2Event:用于端到端事件提取的可控序列到结构生成

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

University of Chinese Academy of Sciences(中国科学院大学);Tencent Inc.(腾讯公司);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)

Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, Shaoyi Chen

摘要:

由于事件记录的复杂结构以及文本和事件之间的语义鸿沟,事件提取具有挑战性。传统的方法通常通过将复杂的结构预测任务分解为多个子任务来提取事件记录。在本文中,我们提出了Text2Event,一个序列到结构的生成范式,可以直接提取事件的文本在一个端到端的方式。具体而言,我们设计了一个统一的事件提取的序列到结构网络,在推理过程中的事件知识注入的约束解码算法,和一个有效的模型学习的课程学习算法。实验结果表明,通过统一建模的所有任务在一个单一的模型和普遍预测不同的标签,我们的方法可以实现竞争力的性能,只使用记录级的注释在监督学习和迁移学习设置。

英文摘要:

Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple subtasks. In this paper, we propose Text2Event, a sequence-to-structure generation paradigm that can directly extract events from the text in an end-to-end manner. Specifically, we design a sequence-to-structure network for unified event extraction, a constrained decoding algorithm for event knowledge injection during inference, and a curriculum learning algorithm for efficient model learning. Experimental results show that, by uniformly modeling all tasks in a single model and universally predicting different labels, our method can achieve competitive performance using only record-level annotations in both supervised learning and transfer learning settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑