Using Cost-Sensitive Ranking Loss to Improve Distant Supervised Relation Extraction
Recently,many researchers have concentrated on using neu-ral networks to learn features for Distant Supervised Relation Extraction(DSRE).However,these approaches generally employ a softmax classi-fier with cross-entropy loss,and bring the noise of artificial class NA into classification process.Moreover,the class imbalance problem is serious in the automatically labeled data,and results in poor classification rates on minor classes in traditional approaches.In this work,we exploit cost-sensitive ranking loss to improve DSRE.It first uses a Piecewise Convolutional Neural Network(PCNN)to embed the semantics of sentences.Then the features are fed into a classifier which takes into account both the ranking loss and cost-sensitive.Ex-periments show that our method is effective and performs better than state-of-the-art methods.
Daojian Zeng Junxin Zeng Yuan Dai
Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation,School of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410004,P.R.China
国内会议
第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会
南京
英文
1-12
2017-10-13（万方平台首次上网日期，不代表论文的发表时间）