arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10249cs.CLcs.AI
收藏

内部和贯穿的实体结构:为文档级关系抽取建模提及规则

Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction

Baidu Inc.(百度公司)

Benfeng Xu, Quan Wang, Yajuan Lyu, Yong Zhu, Zhendong Mao

摘要:

实体作为关系抽取任务中的基本元素,具有一定的结构性。在这项工作中,我们制定了这样的结构提到对之间的独特的依赖关系。然后,我们提出了SSAN,它将这些结构的依赖性内的标准自我注意力机制,并在整个编码阶段。具体来说,我们在每个自我注意构建块内设计了两个替代转换模块来产生注意偏差,从而自适应地调整其注意流。我们的实验证明了所提出的实体结构和SSAN的有效性。它显著优于竞争基准,在三个流行的文档级关系抽取数据集上获得了最新的结果。我们进一步提供消融和可视化来展示实体结构如何引导模型以获得更好的关系抽取。我们的代码是公开的。

英文摘要:

Entities, as the essential elements in relation extraction tasks, exhibit certain structure. In this work, we formulate such structure as distinctive dependencies between mention pairs. We then propose SSAN, which incorporates these structural dependencies within the standard self-attention mechanism and throughout the overall encoding stage. Specifically, we design two alternative transformation modules inside each self-attention building block to produce attentive biases so as to adaptively regularize its attention flow. Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN. It significantly outperforms competitive baselines, achieving new state-of-the-art results on three popular document-level relation extraction datasets. We further provide ablation and visualization to show how the entity structure guides the model for better relation extraction. Our code is publicly available.

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。

↑