用于方面级情感分析的图指导的差异化注意力网络

PDF(3189 KB)

中文信息学报 ›› 2023, Vol. 37 ›› Issue (7) : 102-113.

情感分析与社会计算

张文轩,殷雁君

作者信息 +

Graph-guided Differentiated Attention Network for Aspect-Level Sentiment Analysis

ZHANG Wenxuan, YIN Yanjun

Author information +

History +

摘要

方面级情感分析旨在识别句子中每个方面的情感极性。近年来,将注意力机制和依存树语法结构信息相结合的方法被用于建模方面项和意见项间的依赖关系。然而,这类方法通常具有高度依赖依存树解析质量的缺点。此外,注意力机制也存在因权重分布密集而引入噪声的固有缺陷。为解决以上问题,该文设计并提出了用于方面级情感分析的图指导的差异化注意力网络模型。模型利用图指导机制帮助自注意力机制主动学习接近语法结构的注意力权重,减轻模型对依存树的依赖程度。同时利用注意力差异化操作鼓励注意力权重分布趋于离散,以有效减少噪声引入。在3个公开数据集上进行的实验,验证了该文所提出的方法能更合理地利用语义和语法信息,具有较为先进的情感分类性能。

Abstract

Aspect-level sentiment analysis aims to identify the sentiment polarity of each aspect in a sentence. To better combine the attention mechanism with the dependency tree, this paper proposes a graph guided differentiated attention network for aspect-level sentiment analysis. In order to alleviate the effect of parsing errors, a graph guidance mechanism is used to help the self attention mechanism actively learn the attention weight close to the grammatical structure and reduce the dependence of the model on the dependency tree. Meanwhile, in order to reduce the introduction of noise, an attention differentiation operation is used to encourage the attention weight distribution to be discrete. Experiments on three public datasets show that the proposed method can improve sentiment classification performance.

导出引用

张文轩,殷雁君. 用于方面级情感分析的图指导的差异化注意力网络. 中文信息学报. 2023, 37(7): 102-113

ZHANG Wenxuan, YIN Yanjun. Graph-guided Differentiated Attention Network for Aspect-Level Sentiment Analysis. Journal of Chinese Information Processing. 2023, 37(7): 102-113

参考文献

[1] LIU B. Sentiment analysis and opinion mining [J]. Synthesis Lectures on Human Language Technologies, 2012, 5(1): 1-167.
[2] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[3] PETERS B, NICULAE V, MARTINS A F T. Sparse sequence-to-sequence models [C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 1504-1519.
[4] CORREIA G M, NICULAE V, MARTINS A F T. Adaptively sparse transformers [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 2174-2184.
[5] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks [C]//Proceedings of the 5th International Conference on Learning Representations, Toulon, France, 2017.
[6] HUANG B, CARLEY K M. Syntax-aware aspect level sentiment classification with graph attention networks [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 5469-5477.
[7] WANG K, SHEN W, YANG Y, et al. Relational graph attention network for aspect-based sentiment analysis [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 3229-3238.
[8] BAI X, LIU P, ZHANG Y. Investigating typed syntactic dependencies for targeted sentiment classification using graph attention neural network [J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 503-514.
[9] XU G, LIU P, ZHU Z, et al. Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention[J]. Applied Sciences, 2021, 11(8): 2076-3417.
[10] CHEN C, TENG Z, ZHANG Y. Inducing target-specific latent structures for aspect sentiment classification [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 5596-5607.
[11] TANG H, JI D, LI C, et al. Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 6578-6588.
[12] LI R, CHEN H, FENG F, et al.Dual graph convolutional networks for aspect-based sentiment analysis [C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 6319-6329.
[13] KIRITCHENKO S, ZHU X, CHERRY C, et al. NRC-Canada-2014: Detecting aspects and sentiment in customer reviews [C]//Proceedings of the 8th International Workshop on Semantic Evaluation, 2014: 437-442.
[14] WANG Y, HUANG M, ZHU X, et al.Attention-based LSTM for aspect-level sentiment classification [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 606-615.
[15] MA D, LI S, ZHANG X, et al.Interactive attention networks for aspect-level sentiment classification [C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017: 4068-4074.
[16] FAN F, FENG Y, ZHAO D. Multi-grained attention network for aspect-level sentiment classification [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 3433-3442.
[17] HUANG B, OU Y, CARLEY K M. Aspect level sentiment classification with attention-over-attention neural networks [C]//Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation. Springer, Cham, 2018: 197-206.
[18] CHEN D, MANNING C D. A fast and accurate dependency parser using neural networks [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014: 740-750.
[19] ZHANG C, LI Q C, SONG D W. Aspect-based sentiment classification with aspect-specific graph convolutional networks [C]//Proceedings of the Conference on Emprical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hongkong Association for Computational Linguistics, 2019: 4568-4578.
[20] ZHANG M, QIAN T. Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 3540-3549.
[21] HOU X, HUANG J, WANG G, et al. Selective attention based graph convolutional networks for aspect-level sentiment classification [C]//Proceedings of the 15th Workshop on Graph-Based Methods for Natural Language Processing, 2021: 83-93.
[22] SUN K, ZHANG R, MENSAH S, et al. Aspect-level sentiment analysis via convolution over dependency tree [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019: 5679-5688.
[23] VELICˇKOVIC＇ P, CUCURULL G, CASANOVA A, et al. Graph attention networks [C]//Proceedings of the 6th International Conference on Learning Representations, Vancouver, Canada, 2018: 1-12.
[24] ZHANG J, CHEN C, LIU P, et al. Target-guided structured attention network for target-dependent sentiment analysis [J]. Transactions of the Association for Computational Linguistics,2020,8: 172-182.
[25] PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. Semeval-2014 task 4: Aspect based sentiment analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation, Dublin, Ireland, 2014: 27-35.
[26] DONG L, WEI F, TAN C, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification [C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014: 49-54.
[27] PENNINGTON J, SOCHER R, MANNING C D. Glove: Global vectors for word representation [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014: 1532-1543.
[28] TANG D, QIN B, LIU T. Aspect level sentiment classification with deep memory network [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 214-224.
[29] LI X, BING L, LAM W, et al. Transformation networks for target-oriented sentiment classification [C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 946-956.
[30] PENG H, XU L, BING L, et al. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis [C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(05): 8600-8607.

基金

内蒙古自治区自然科学基金(2021LHMS06009)

PDF(3189 KB)

808

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金



Issue Date
2023-09-17