论文标题
Hiclre：用于远距离监督关系提取的分层对比学习框架
HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction
论文作者
论文摘要
遥远的监督假设任何包含相同实体对的句子都反映了相同的关系。以前的远距离监督关系提取（DSRE）任务的工作通常集中在句子级别或行李级级别的去命中技术上，从而忽略了与交叉级别的明确相互作用。在本文中，我们提出了一个分层对比度学习框架，以远距离监督的关系提取（打Hiclre）来减少嘈杂的句子，以整合全球结构信息和局部细粒度的相互作用。具体而言，我们提出了一个三级层次学习框架，以与跨层相互作用，从而通过调整现有的多头自我注意力（称为多范围的重新连接化）来产生掉额的上下文感知表示。同时，还以基于动态梯度的数据增强策略为对比度学习的特定水平也提供了伪阳性样品，该策略称为动态梯度对抗扰动。实验表明，在各种主流DSRE数据集中，HICLRE明显胜过强大的基准。
Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level de-noising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a hierarchical contrastive learning Framework for Distantly Supervised relation extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multi-head self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.
