arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.06125cs.CLcs.LG
收藏

基于图的深度偏仿射注意模型的时态关系抽取

Temporal Relation Extraction with a Graph-Based Deep Biaffine Attention Model

University of California, San Diego(加利福尼亚大学圣迭戈分校);Hong Kong University of Science and Technology(香港科技大学);National Taiwan University(国立台湾大学)

Bo-Ying Su, Shang-Ling Hsu, Kuan-Yin Lai, Amarnath Gupta

摘要:

时间信息抽取在自然语言理解中起着至关重要的作用。以前的系统已经结合了先进的神经语言模型,并成功地提高了时间信息抽取任务的准确性。然而,这些系统有两个主要缺点。首先,他们没有利用预测中时间关系的双面性。其次,它们在推理过程中涉及不可并行的流水线,带来的性能增益很小。为此,我们提出了一种新的时间信息抽取模型的基础上,深度biaffine注意,提取时间之间的关系,在非结构化文本中的事件有效和准确。我们的模型是高性能的,因为我们直接执行关系抽取任务,而不是考虑事件注释作为关系抽取的先决条件。此外,我们的架构使用多层感知器(MLP)与biaffine注意分别预测弧和关系标签,提高关系检测的准确性,利用双边性质的时间关系。我们的实验表明,我们的模型达到国家的最先进的性能在时间关系抽取。

英文摘要:

Temporal information extraction plays a critical role in natural language understanding. Previous systems have incorporated advanced neural language models and have successfully enhanced the accuracy of temporal information extraction tasks. However, these systems have two major shortcomings. First, they fail to make use of the two-sided nature of temporal relations in prediction. Second, they involve non-parallelizable pipelines in inference process that bring little performance gain. To this end, we propose a novel temporal information extraction model based on deep biaffine attention to extract temporal relationships between events in unstructured text efficiently and accurately. Our model is performant because we perform relation extraction tasks directly instead of considering event annotation as a prerequisite of relation extraction. Moreover, our architecture uses Multilayer Perceptrons (MLP) with biaffine attention to predict arcs and relation labels separately, improving relation detecting accuracy by exploiting the two-sided nature of temporal relationships. We experimentally demonstrate that our model achieves state-of-the-art performance in temporal relation extraction.

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。

↑