论文标题
充分利用比喻识别
Getting the Most out of Simile Recognition
论文作者
论文摘要
明喻识别涉及两个子任务：明词句子分类，该分类区分句子是否包含比喻，而比喻组件提取可以找到相应的对象（即男高音和车辆）。最近的工作忽略了表面字符串以外的其他功能。在本文中，我们探讨了此任务的表达功能，以实现更有效的数据利用。特别是我们研究了两种类型的功能：1）输入侧特征，包括POS标签，依赖树和单词定义以及2）解码功能，这些特征捕获了各种解码决策之间相互依存关系。我们进一步构建了一个名为HGSR的模型，该模型将输入端特征合并为异质图，并通过蒸馏利用解码功能。实验表明，HGSR显着胜过当前的最新系统和精心设计的基线，从而验证了引入特征的有效性。我们的代码可在https://github.com/deeplearnxmu/hgsr上找到。
Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i.e., tenors and vehicles). Recent work ignores features other than surface strings. In this paper, we explore expressive features for this task to achieve more effective data utilization. Particularly, we study two types of features: 1) input-side features that include POS tags, dependency trees and word definitions, and 2) decoding features that capture the interdependence among various decoding decisions. We further construct a model named HGSR, which merges the input-side features as a heterogeneous graph and leverages decoding features via distillation. Experiments show that HGSR significantly outperforms the current state-of-the-art systems and carefully designed baselines, verifying the effectiveness of introduced features. Our code is available at https://github.com/DeepLearnXMU/HGSR.
