多任务交互式学习网络的方面情感分析

doi:10.3778/j.issn.1002-8331.2203-0485

摘要/Abstract

摘要： 方面情感分析传统方法采用方面词抽取-情感预测的独立学习模式，未充分利用两模块的联合信息及训练过程中有价值的信息。提出基于消息传递机制的多任务交互式学习网络，模型采用细粒度属性级分类任务和篇章级分类任务联合训练，设计消息传递显式地对任务交互进行建模，通过共享隐藏变量迭代传递信息，有助于特征学习和推理。方面情感分析模块提出词级信息交互机制以及观点词抽取——情感预测信息传递通道，实现双注意力机制；利用池化操作嵌入多层GRU网络实现篇章级任务预测。设计迭代算法在方面级和篇章级任务间交替训练，通过三个数据集上的实验对比，结果表明模型在每个子任务的F1分数、模型整体性能、篇章级任务网络性能上均得到有效提高。

关键词: 方面情感, 多任务交互, 消息传递机制, 词级交互, 双注意力

Abstract: The traditional method of aspect-based sentiment analysis adopts the independent model of aspect-word extraction and emotion prediction, which does not fully utilize the joint information and the valuable information in the training process. Multi-tasking interactive learning network based on message passing mechanism is proposed, which using fine-grained property level task and chapter level task joint training. A message passing mechanism explicitly to modeling of interactions between tasks is designed, by sharing hidden variable iteration pass information. Word-level information interaction module and aspect opinion-word extraction/aspect sentiment prediction information transmission channel are designed to realize the dual attention mechanism. Multi layer GRU network combined with pooling operation is used to realize chapter level task prediction. Iterative algorithm is designed on three data sets to train alternately between aspect and chapter tasks. The effectiveness and feasibility of the model are verified by comparing the F1 score of each task, the overall performance of the model, and the network performance of the discourse level task.

Key words: aspect emotion, multi-task interaction;message passing mechanism;word-level interaction, dual attention

宋婷, 潘理虎, 陈战伟. 多任务交互式学习网络的方面情感分析[J]. 计算机工程与应用, 2022, 58(19): 202-208.

SONG Ting, PAN Lihu, CHEN Zhanwei. Aspect Sentiment Analysis Based on Multi-Task Interactive Learning Network[J]. Computer Engineering and Applications, 2022, 58(19): 202-208.

参考文献

[1] PANG B，LEE L.Opinion mining and sentiment analysis[J].Foundations and Trends in Information Retrieval，2008，2（1/2）：1-135.
[2] ZHANG L，LIU B.Sentiment analysis and opinion mining[M].Morgan：Claypool Publishers，2017：1-50.
[3] 刘全，梁斌，周倩.一种用于基于方面情感分析的深度分层网络模型[J].计算机学报，2018，41（12）：2637-2652.
LIU Q，LIANG B，ZHOU Q.A deep hierarchical network model for aspect?based sentiment analysis[J].Chinese Journal of Computers，2018，41（12）：2637-2652.
[4] XIN L，BING L，LI P，et al.Aspect term extraction with history attention and selective transformation[C]//Proceedings of International Joint Conference on Artificial Intelligence，2019：4194-4200.
[5] HU X，BING L，LEI S，et al.Double embedding and CNN-based sequence labeling for aspect extraction[C]//Proceedings of Annual Meeting of the Association for Computational Linguistics，2018.
[6] WANG W，PAN S J，DANIEL D，et al.Coupled multi-layer attentions for co-extraction of aspect and opinion terms[C]//Proceedings of AAAI Conference on Artificial Intelligence，2017.
[7] LSMADI M，TALAFHA B，ALAYYOUB M，et al.Using long short-term memory deep neural networks for aspect-base sentiment analysis of arabic reviews[J].International Journal of Machine Learning and Cybernetics，2019，10（8）：2163-2175.
[8] ZHAO A，YU Y.Knowledge-enabled BERT for aspect-based sentiment analysis[J].Knowledge-Based Systems，2021，227（2）：10722.
[9] PENG H，XU L，BING L，et al.A near complete solution for aspect-based sentiment analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：8600-8607.
[10] JIANG Z L，GAO S，CHEN L C.Study on text representation method based on deep learning and topic information[J].Computing，2019，102：623-642.
[11] XU R，CHEN J Y，HAN J，et al.Deep learning-based facial expression analysis using ordinal information[J].Computing，2019，102：765-780.
[12] SU J，ZENG J，DEYI X A.Hierarchy-to-sequence attentional neural machine translation model[J].IEEE/ACM Transactions on Audio Speech & Language Processing，2018，26（3）：623-632.
[13] LI X，BING L D，LI P J，et al.A unified model for opinion target extraction and target sentiment prediction[C]//Proceedings of AAAI Conference on Artificial Intelligence，2019：6714-6721.
[14] WANG X，XU G，ZHANG Z，et al.End-to-end aspect-based sentiment analysis with hierarchical multi-task learning[J].Neurocomputing，2021，455：178-188.
[15] YAN X，LIN N，LIN X，et al.An indonesian sentiment classification model based on multi-task learning[C]//Advances in Natural Computation，Fuzzy Systems and Knowledge Discovery，2021：1182-1191.
[16] 梁斌，刘全，徐进，等.基于多注意力卷积神经网络的特定目标情感分[J].计算机研究与发展，2017，54（8）：1724-1735.
LIANG B，LIU Q，XU J，et al.Target-specific sentiment score based on multi-attention convolutional neural network[J].Computer Research and Development，2017，54（8）：1724-1735.
[17] WANG Y，HUANG M，ZHAO L.Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing，2016：606-615.
[18] HE R D，LEE W S，NG H T.Effective attention modeling for aspect-level sentiment classification[C]//Proceedings of International Conference on Computational Linguistics，2018：25-30.
[19] KUMAR A，GUPTA P，BALAN R，et al.BERT based semi-supervised hybrid approach for aspect and sentiment classification[J].Neural Processing Letters，2021，53：4207-4224.
[20] WANG F，LAN M，WANG W.Towards a one-stop solution to both aspect extraction and sentiment analysis tasks with neural multi-task learning[C]//Proceedings of 2018 International Joint Conference on Neural Networks，2018：1-8.
[21] DAI J，YAN H，SUN T，et al.Does syntax matter? a strong baseline for aspect-based sentiment analysis with roberta[J].arXiv：2104.04986，2021.
[22] LI Z，ZOU Y，ZHANG C，et al.Learning implicit sentiment in aspect-based sentiment analysis with supervised contrastive pre-training[J].arXiv：2111.02194，2021.