摘要
针对实体关系抽取任务中,传统基于统计学习的方法构建特征费时费力、现有深度学习方法依赖单一词向量的表征能力的问题,提出多通道卷积神经网模型。使用不同的词向量将输入语句进行映射,作为模型不同通道的输入,然后使用卷积神经网自动提取特征,通过softmax分类器输出关系类型,完成关系抽取任务。与其他模型相比,该模型可以获取输入语句更丰富的语义信息,自动学习出更具有区分度的特征。在Sem Eval-2010 Task 8数据集上的实验结果表明提出的多通道卷积神经网模型较使用单一词向量的模型更适合处理关系抽取任务。
In the task of relation extraction,traditional statistical methods have difficulties in getting perfect features manually,while deep learning methods strongly depend on the representational capacity of single word vector. To solve the problems mentioned above,this paper proposed a novel model called multi-channel convolutional neural network( CNN). Firstly,the model used different word vectors to represent sentence as input for different channels. Secondly,it extracted features automatically through CNN. Finally,it obtained relation types by using softmax classifier. The proposed model could capture more semantic information thus it learned more distinctive features automatically comparing to other models. The experiment results on Sem Eval-2010 Task 8 datasets show that the proposed model is more suitable for relation extraction task than normal models which only utilize single word vector.
出处
《计算机应用研究》
CSCD
北大核心
2017年第3期689-692,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(61331017
41501485)
关键词
关系抽取
卷积神经网
深度学习
多通道
relation extraction
convolutional neural network
deep learning
multi-channel