Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
复制标题
DOI：
10.18653/v1/d15-1062
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
Kun Xu;Yansong Feng;Songfang Huang;Dongyan Zhao
中科院分区：
文献类型：
--
作者：
Kun Xu;Yansong Feng;Songfang Huang;Dongyan Zhao
句法特征在确定句子中的关系方面起着至关重要的作用。先前的神经网络模型直接作用于原始词序列或成分句法分析树，因此当主语和宾语距离较远时，常常会受到无关信息的干扰。在本文中，我们提议通过卷积神经网络从最短依存路径中学习更稳健的关系表征。我们进一步考虑关系方向性，并提出一种简单的负采样策略来改进主语和宾语的分配。实验结果表明，我们的方法在SemEval - 2010任务8数据集上优于最先进的方法。
Syntactic features play an essential role in identifying relationship in a sentence. Previous neural network models directly work on raw word sequences or constituent parse trees, thus often suffer from irrelevant information introduced when subjects and objects are in a long distance. In this paper, we propose to learn more robust relation representations from shortest dependency paths through a convolution neural network. We further take the relation directionality into account and propose a straightforward negative sampling strategy to improve the assignment of subjects and objects. Experimental results show that our method outperforms the state-of-theart approaches on the SemEval-2010 Task 8 dataset.