基于多任务预训练模型的属性级情感分类  

Aspect-level Sentiment Classification Based on Multi-Task Pre-Training Model

作　　者：周敏 王中卿[1] 李寿山[1] 周国栋[1] ZHOU Min;WANG Zhongqing;LI Shoushan;ZHOU Guodang(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China)

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《中文信息学报》2022年第10期126-134,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(62076175,61976146);江苏省双创博士计划。

摘　　要：目前,缺少标注样本数据是属性级情感分类任务面临的一大难题,为了解决这一问题,该文提出了结合多项任务的预训练Bert模型。该模型利用大量未标注的篇章级情感分类数据,结合多种分类任务预训练模型共享参数,迁移属性级评论和篇章级评论中共享的有用的语义语法信息,从而帮助模型提高属性级情感分类准确率。在SemEval-14数据集上的实验结果表明,相较于一系列基准模型,该文提出的模型有效提高了属性级情感分类的准确率。The lack of annotated sample has become a major challenge for aspect-level sentiment classification.This paper proposes a combined multi-task pre-training Bert model to alleviate this issue.A large amount of unlabeled document-level sentiment classification data is employed to train a variety of classification tasks for a pre-trained model with share parameters,so as to transfer the useful semantic and grammatical information shared between aspect-level comments and document-level comments.Experiments on the SemEval-14 data set show that,compared with a series of baseline models,the model proposed in this paper effectively improves the accuracy of aspect-level sentiment classification.

关 键 词：Bert 多任务 情感分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]