方面级情感分类是一种细粒度的情感分析任务,旨在分类出文本中不同方面的情感。目前,现有方面级情感分类模型存在特征提取层次浅、泛化能力弱等问题。为此,该文提出一种基于融合对抗网络的方面级情感分类模型ASFAN(Aspect-level Sentiment classification model based on Fusion Adversarial Networks)。首先,从数据集中提取文本的方面词、位置、上下文信息表示。其次,将方面词、位置、上下文信息通过BERT编码。最后,通过多头注意力和局部注意力机制提取文本特征,将特征进行融合学习。此外,通过对抗学习算法生成对抗样本,将对抗样本作为一种文本数据增强样本,优化决策边界。实验结果表明,在SemEval 2014的Restaurant、Laptop数据集和ACL-2014的Twitter数据集上,ASFAN的准确率分别达86.54%、79.15%、76.16%,ASFAN对比大多数基线模型性能提升显著。
Abstract
Aspect-level sentiment classification is a fine-grained sentiment analysis task that aims to classify the sentiment of different aspects of a text., Existing aspect-level sentiment classification models have problems such as shallow feature extraction level and weak generalization ability. Therefore, we propose an aspect-level sentiment classification model based on fusion adversarial networks. Firstly, the aspect words, location, and contextual information representation of the text are extracted from the dataset. Secondly, the information of aspect words, position, and context is encoded by BERT. Finally, text features are extracted by multiple attention and local attention mechanisms, and then fused for learning. Moreover, the adversarial learning algorithm is used to generate adversarial samples, which are used as a kind of textual data augmentation to optimize the decision boundary. The experimental results show that the accuracy of the proposed method reaches 86.54%, 79.15%, and 76.16% on the Restaurant and Laptop datasets of SemEval 2014 and the Twitter dataset of ACL-2014, respectively, outperforming most baseline models.
关键词
方面级情感分类 /
注意力机制 /
融合对抗网络 /
BERT /
对抗样本
{{custom_keyword}} /
Key words
aspect-level sentiment classification /
attention mechanism /
fusion adversarial networks /
BERT /
adversarial samples
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 钟佳娃, 刘巍, 王思丽, 等. 文本情感分析方法及应用综述[J]. 数据分析与知识发现, 2021,5(06): 1-13.
[2] 赵妍妍, 秦兵, 石秋慧, 等. 大规模情感词典的构建及其在情感分类中的应用[J]. 中文信息学报, 2017, 31(02): 187-193.
[3] 郗亚辉. 产品评论中领域情感词典的构建[J]. 中文信息学报, 2016, 30(05): 136-144.
[4] 翟学明, 魏巍. 混合神经网络和条件随机场相结合的文本情感分析[J]. 智能系统学报, 2021,16(02): 202-209.
[5] 黄佳锋, 薛云, 卢昕, 等. 面向中文网络评论情感分类的集成学习框架[J]. 中文信息学报, 2018, 32(09): 113-122.
[6] 王光, 李鸿宇, 邱云飞, 等. 基于图卷积记忆网络的方面级情感分类[J]. 中文信息学报, 2021, 35(08): 98-106.
[7] 曾锋, 曾碧卿, 韩旭丽, 等. 基于双层注意力循环神经网络的方面级情感分析[J]. 中文信息学报, 2019, 33(06): 108-115.
[8] ZENG B, YANG H, XU R, et al. LCF: A local context focus mechanism for aspect-based sentiment classification[J]. Applied Sciences, 2019, 9(16): 3389.
[9] BIGGIO B, ROLI F. Wild patterns: Ten years after the rise of adversarial machine learning[J]. Pattern Recognition, 2018, 84: 317-331.
[10] GOODFELLOW I J, SHLENS J, SZEGEDY C. Explaining and harnessing adversarial examples[C]//Proceedings of the 3rd International Conference on Learning Representations, USA, 2015.
[11] MIYATO T, DAI A M, GOODFELLOW I J. Adversarial training methods for semi-supervised text classification[C]//Proceedings of the 5th International Conference on Learning Representations, France, 2017.
[12] MADRY A, MAKELOV A, SCHMIDT L, et al. Towards deep learning models resistant to adversarial attacks[C]//Proceedings of the 6th International Conference on Learning Representations, Canada, 2018.
[13] SHAFAHI A, NAJIBI M, GHIASI A, et al. Adversarial training for free![C]//Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems,Canada, 2019: 3353-3364.
[14] ZHANG D, ZHANG T, LU Y, et al. You only propagate once: accelerating adversarial training via maximal principle[C]//Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems, Canada, 2019: 227-238.
[15] ZHU C, CHENG Y, GAN Z, et al. FreeLB: Enhanced adversarial training for natural language understanding[C]//Proceedings of the 8th International Conference on Learning Representations, Ethiopia, 2020.
[16] JIANG H, HE P, CHEN W, et al. SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: Association for Computational Linguistics, 2020: 2177-2190.
[17] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017: 5998-6008.
[18] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, 2019: 4171-4186.
[19] 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: Association for Computational Linguistics, 2014: 27-35.
[20] 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. Baltimore, Maryland: Association for Computational Linguistics, 2014: 49-54.
[21] 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. Australia, 2017: 4068-4074.
[22] CHEN P, SUN Z, BING L, et al. Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark: Association for Computational Linguistics, 2017: 452-461.
[23] 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. Brussels, Belgium: Association for Computational Linguistics, 2018: 3433-3442.
[24] 杨玉亭, 冯林, 代磊超, 等. 面向上下文注意力联合学习网络的方面级情感分类模型[J]. 模式识别与人工智能, 2020, 33(08): 753-765.
[25] YANG Y T, FENG L, DAI L C. A BERT-based interactive attention network for aspect sentiment analysis[J]. Journal of Computers, 2021, 32(3): 30-42.
[26] ZHANG C, LI Q, SONG D. Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China: Association for Computational Linguistics, 2019: 4568-4578.
[27] YANG H, ZENG B, XU M, et al. Back to reality: Leveraging pattern-driven modeling to enable affordable sentiment dependency learning[J]. arXiv: 2110.08604 [cs], 2021.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(71971151,61876158)
{{custom_fund}}
PDF(1443 KB)
