APP下载

基于PU学习的建议语句分类方法

2019-07-31张璞刘畅李逍

计算机应用 2019年3期

张璞 刘畅 李逍

摘 要:建议挖掘作为一项新兴研究任务,具有重要的应用价值。针对传统建议语句分类方法所存在的规则复杂、标注工作量大、特征维度高、数据稀疏等问题,提出一种基于PU学习的建议语句分类方法。首先,使用简单规则从无标注评论集合中选择建议语句的正例集合;然后,为了降低特征维度,缓解数据稀疏性,在自编码神经网络(Autoencoder)特征空间中使用Spy技术划分可靠反例集合;最后,利用正例集合和可靠反例集合来训练多层感知机(MLP)对剩余的无标注样例进行分类。该方法在中文数据集上的F1值和准确率值分别达到81.98%和82.67%,实验结果表明,该方法能够有效地对建议语句进行分类,且不需要对数据进行人工标注。

关键词:建议挖掘;建议语句分类;PU学习;自编码神经网络器;多层感知机

中图分类号: TP391

文献标志码:A

文章编号:1001-9081(2019)03-0639-05

Abstract: As a new research task, suggestion mining has important application value. Since traditional suggestion sentence classification methods have problems like complex rules, large labeling workload, high feature dimension and data sparsity, a PU (Positive and Unlabeled)-based suggestion sentence classification method was proposed. Firstly, some suggestion sentences were selected from an unlabeled review set by using a simple rule to form a positive example set; then a reliable negative example set was constructed by Spy technique in the feature space of autoencoder neural network to reduce the feature dimension and alleviate data sparsity; finally, Multi-Layer Perceptron (MLP) was trained by the positive example set and the reliable negative example set to classify the remaining unlabeled samples. On a Chinese dataset, the F1 value and the accuracy of the proposed method, reached 81.98% and 82.67% respectively. The experimental results show that the proposed method can classify suggestion sentences effectively without manually labelling the data.

Key words: suggestion mining; suggestion sentence classification; PU (Positive and Unlabeled) learning; autoencoder; Multi-Layer Perceptron (MLP)

0 引言

隨着互联网的快速发展,网络上出现了海量的用户评论,人们不仅会在评论中传达积极或消极的情绪,有时也会对产品、服务等提出相应的建议。例如,在“希望三星手机能支持谷歌应用商店”这条评论中虽然并未包含情感极性,但明确提出了对产品功能的改进建议。这类建议信息可以帮助厂家有效地提升产品质量,也有助于商家有针对性地制定销售策略,具有重要的应用价值,建议挖掘[1]研究因此应运而生。

进行建议挖掘,首先需要对建议语句进行分类,即将评论语句分为建议语句或非建议语句。但由于人们对建议的判定存在比较大的主观性,导致建议语句的定义难以取得一致,这给语料标注和问题定义带来了很多困难[1]。……

登录APP查看全文