论文标题
正规化的专注胶囊网络，用于重叠的关系提取
Regularized Attentive Capsule Network for Overlapped Relation Extraction
论文作者
论文摘要
由于人类对人的努力的要求较少，因此遥远的监督关系提取已被广泛应用于知识库的构建中。但是，在遥远的监督中自动建立的培训数据集包含嘈杂的单词和重叠关系的低质量实例，这为准确提取关系带来了巨大的挑战。为了解决这个问题，我们提出了一个新颖的正规化胶囊网络（RA-CAPNET），以更好地识别每个非正式句子中高度重叠的关系。为了发现一个实例中的多个关系特征，我们将多头注意力嵌入胶囊网络中，作为低级胶囊，在其中两个实体的减法是一种新的关系查询形式，以选择显着特征，无论其位置如何。为了进一步区分重叠的关系特征，我们设计了分歧正规化，以明确鼓励多个注意力头和低级胶囊之间的多样性。在广泛使用的数据集上进行的广泛实验表明，我们的模型在关系提取方面取得了重大改进。
Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established training datasets in distant supervision contain low-quality instances with noisy words and overlapped relations, introducing great challenges to the accurate extraction of relations. To address this problem, we propose a novel Regularized Attentive Capsule Network (RA-CapNet) to better identify highly overlapped relations in each informal sentence. To discover multiple relation features in an instance, we embed multi-head attention into the capsule network as the low-level capsules, where the subtraction of two entities acts as a new form of relation query to select salient features regardless of their positions. To further discriminate overlapped relation features, we devise disagreement regularization to explicitly encourage the diversity among both multiple attention heads and low-level capsules. Extensive experiments conducted on widely used datasets show that our model achieves significant improvements in relation extraction.
