论文标题
Autorc：通过架构搜索改善基于BERT的关系分类模型
AutoRC: Improving BERT Based Relation Classification Models via Architecture Search
论文作者
论文摘要
尽管基于BERT的关系分类（RC）模型对传统的深度学习模型取得了重大改进，但似乎无法就最佳体系结构达成共识。首先，有多种用于实体跨度识别的替代方案。其次，有一系列集合操作将实体和上下文的表示形式汇总为固定长度向量。第三，很难手动确定哪些特征向量（包括其相互作用）有益于对关系类型进行分类。在这项工作中，我们为基于BERT的RC模型设计了一个全面的搜索空间，并采用神经体系结构搜索（NAS）方法自动发现上述设计选择。在七个基准RC任务上进行的实验表明，与基线BERT基于BERT的RC模型相比，我们的方法在寻找更好的架构方面是有效的。消融研究证明了我们的搜索空间设计的必要性以及我们搜索方法的有效性。
Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached on what is the optimal architecture. Firstly, there are multiple alternatives for entity span identification. Second, there are a collection of pooling operations to aggregate the representations of entities and contexts into fixed length vectors. Third, it is difficult to manually decide which feature vectors, including their interactions, are beneficial for classifying the relation types. In this work, we design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices mentioned above. Experiments on seven benchmark RC tasks show that our method is efficient and effective in finding better architectures than the baseline BERT based RC model. Ablation study demonstrates the necessity of our search space design and the effectiveness of our search method.
