Composing Distributed Representations of Relational Patterns
Composing Distributed Representations of Relational Patterns
复制标题
DOI：
10.18653/v1/p16-1215
复制
发表时间：
2016-08
期刊：
影响因子：
--
通讯作者：
Sho Takase;Naoaki Okazaki;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Sho Takase;Naoaki Okazaki;Kentaro Inui
学习关系实例的分布式表示是下游NLP应用中的一项核心技术。为了解决关系模式的语义建模问题，本文构造了一个新的数据集，为现有数据集上的每一对关系模式提供多个相似度评级。此外，我们还对不同的编码器进行了比较研究，包括加性组合、RNN、LSTM和GRU，用于组成关系模式的分布式表示。我们还提出了栅极添加剂组合物，它是添加剂组合物与浇注机制的增强。实验表明，新的数据集不仅能够对不同的编码者进行详细的分析，而且还提供了一种度量标准，用于预测关系模式的分布式表示在关系分类任务中的成功与否。
Learning distributed representations for relation instances is a central technique in downstream NLP applications. In order to address semantic modeling of relational patterns, this paper constructs a new dataset that provides multiple similarity ratings for every pair of relational patterns on the existing dataset. In addition, we conduct a comparative study of different encoders including additive composition, RNN, LSTM, and GRU for composing distributed representations of relational patterns. We also present Gated Additive Composition, which is an enhancement of additive composition with the gating mechanism. Experiments show that the new dataset does not only enable detailed analyses of the different encoders, but also provides a gauge to predict successes of distributed representations of relational patterns in the relation classification task.