Instance-Based Neural Dependency Parsing
Instance-Based Neural Dependency Parsing
复制标题
DOI：
10.1162/tacl_a_00439
复制
发表时间：
2021-09
影响因子：
10.9
通讯作者：
Hiroki Ouchi;Jun Suzuki;Sosuke Kobayashi;Sho Yokoi;Tatsuki Kuribayashi;Masashi Yoshikawa;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Hiroki Ouchi;Jun Suzuki;Sosuke Kobayashi;Sho Yokoi;Tatsuki Kuribayashi;Masashi Yoshikawa;Kentaro Inui
模型预测的可解释的理论基础在实际应用中是至关重要的。我们开发的神经模型，拥有一个可解释的依赖关系解析推理过程。我们的模型采用基于实例的推理，其中依赖性边缘被提取并通过将它们与训练集中的边缘进行比较来标记。训练边缘被明确地用于预测;因此，很容易掌握每个边缘对预测的贡献。我们的实验表明，我们的基于实例的模型实现了竞争力的准确性与标准的神经模型，并具有合理的基于实例的解释。
Abstract Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.