论文标题
RH-NET：通过增强学习和分层关系搜索改善神经关系提取
RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
论文作者
论文摘要
遥远的监督（DS）旨在产生大规模的启发式标签语料库，该标签库目前广泛用于神经关系提取。但是，它严重遭受了嘈杂的标签和长尾分布问题。许多高级方法通常分别解决两个问题，这些问题忽略了他们的相互作用。在本文中，我们提出了一个名为RH-NET的新型框架，该框架利用强化学习和分层关系搜索模块来改善关系提取。我们利用强化学习来指导模型选择高质量的实例。然后，我们提出了分层的关系搜索模块，以从数据富裕和数据贫乏类之间的相关实例共享语义。在迭代过程中，两个模块不断相互作用，以同时减轻嘈杂和长尾问题。对广泛使用的NYT数据集进行了广泛的实验清楚地表明，我们对最先进的基准的方法进行了重大改进。
Distant supervision (DS) aims to generate large-scale heuristic labeling corpus, which is widely used for neural relation extraction currently. However, it heavily suffers from noisy labeling and long-tail distributions problem. Many advanced approaches usually separately address two problems, which ignore their mutual interactions. In this paper, we propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. We leverage reinforcement learning to instruct the model to select high-quality instances. We then propose the hierarchical relational searching module to share the semantics from correlative instances between data-rich and data-poor classes. During the iterative process, the two modules keep interacting to alleviate the noisy and long-tail problem simultaneously. Extensive experiments on widely used NYT data set clearly show that our method significant improvements over state-of-the-art baselines.
