基于语义对齐与模板可靠性的方面级情感四元组预测

雷子锟 ,  陈彦江 ,  张凯 ,  刘淇

天津大学学报(自然科学与工程技术版) ›› 2026, Vol. 59 ›› Issue (11) : 1187 -1196.

PDF (1113KB)
天津大学学报(自然科学与工程技术版) ›› 2026, Vol. 59 ›› Issue (11) : 1187 -1196. DOI: 10.11784/tdxbz202508010

基于语义对齐与模板可靠性的方面级情感四元组预测

作者信息 +

Aspect Sentiment Quad Prediction via Semantic Matching and Reliable Template Selection

Author information +
文章历史 +
PDF (1138K)

摘要

方面级情感四元组预测(ASQP)任务旨在从文本中同时抽取方面项、方面类别、观点项和情感极性,是情感分析领域中的热门问题.当下主流生成式方法通过多模板引导预训练语言模型生成四元组,然而在进行模板的选取时通常忽视了模板之间潜在的语义关联或各模板本身的性能差异.为此,本文提出一种基于预训练语言模型 T5 的模板可靠性与语义对齐平衡(SMARTS)策略.该策略在模板选择阶段,结合交叉熵和 Jensen-Shannon(JS)散度,构建多个兼顾生成性能与语义关联性的高质量模板分组.首先,以交叉熵作为衡量指标,评估各候选模板在预训练语言模型下的生成性能,筛选出若干生成质量最优的模板;接着,考虑不同模板之间的结构和语义关联,模型进一步引入 JS 散度对模板间的分布差异进行建模,从而为每个性能最优模板匹配若干语义最相关的模板,形成多个高一致性的模板分组.在推理阶段,为充分对齐 SMARTS 策略,本文提出了双层投票聚合策略,先在每组内选出最优结果,再在组间进行全局投票,提升预测稳定性和准确性.在 2 个公开数据集 Rest15 和 Rest16 上实验结果表明了本文所提方法的有效性与优越性,且为了验证各个部分的有效性及更深入了解模型工作原理,文中进行了详细的超参数研究、消融实验以及案例研究.

Abstract

Aspect sentiment quad prediction(ASQP) involves the simultaneous extraction of aspect terms,aspect categories,opinion terms,and sentiment polarities from text,presenting a significant challenge in sentiment analysis. Current mainstream approaches typically employ generative methods that utilize multiple templates to guide pre-trained language models in generating sentiment quads. However,these methods often neglect the semantic relationships between templates and the performance discrepancies among individual templates during the selection process. To overcome these limitations,this study introduces a strategy called semantic matching and reliable templates selection(SMARTS),which is based on the pretrained language model T5 and aims to balance template reliability with semantic alignment. SMARTS first evaluates the generation performance of candidate templates using cross-entropy to filter out those with optimal generation quality. Subsequently,considering the structural and semantic correlations among different templates,it further introduces Jensen-Shannon(JS) divergence to model their distribution differences. This allows SMARTS to match each optimal template with several of the most semantically related ones,thereby forming multiple highly consistent template groups. To align with the SMARTS strategy during inference,a two-stage voting aggregation mechanism is introduced. First,an intra-group voting process identifies the best candidate within each group. Then,a global voting stage aggregates results across groups to determine the final prediction,thereby enhancing both stability and accuracy. Experimental results on two widely-used benchmarks,Rest15 and Rest16,demonstrate the effectiveness and superiority of the proposed model. In addition,extensive experiments,including hyperparameter analysis,ablation studies,and case studies,are conducted to validate the contributions of individual components and to provide deeper insights into the model's behavior.

关键词

方面级情感四元组预测 / 语义对齐 / 预训练语言模型 / 情感分析 / 深度学习

Key words

aspect sentiment quad prediction / semantic matching / pre-trained language models / sentiment analysis / deep learning

引用本文

引用格式 ▾
雷子锟,陈彦江,张凯,刘淇. 基于语义对齐与模板可靠性的方面级情感四元组预测[J]. 天津大学学报(自然科学与工程技术版), 2026, 59(11): 1187-1196 DOI:10.11784/tdxbz202508010

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

郭贤伟, 赖 华, 余正涛, 等. 融合情绪知识的案件微博评论情绪分类[J]. 计算机学报, 2021, 44(3): 564-578.

[2]

Guo Xianwei, Lai Hua, Yu Zhengtao, et al. Emotion classification of case—related microblog comments integrating emotional knowledge[J]. Chinese Journal of Computers, 2021, 44(3): 564-578(in Chinese).

[3]

Luo W, Gong D H. Pre—trained large language models for financial sentiment analysis[EB/OL]. https://arxiv.org/abs/2401.05215, 2024—01—25.

[4]

Bandyopadhyay I, Karmakar R. Deep learning—based sentiment analysis of Olympics tweets[EB/OL]. https://arxiv.org/abs/2407.12376, 2024—07—17.

[5]

Wang Y Q, Huang M L, Zhu X Y, et al. Attention—based LSTM for aspect—level sentiment classification[C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin,USA, 2016: 606-615.

[6]

Tan X W, Cai Y, Zhu C X. Recognizing conflict opinions in aspect—level sentiment classification with dual attention networks[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP—IJCNLP). Hong Kong,China, 2019: 3426-3431.

[7]

Zhang C, Li Q C, Song D W. Aspect—based sentiment classification with aspect—specific graph convolutional networks[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP—IJCNLP). Hong Kong,China, 2019: 4568-4578.

[8]

鲍小异, 姜晓彤, 王中卿, 等. 基于跨语言图神经网络模型的属性级情感分类[J]. 软件学报, 2023, 34(2): 676-689.

[9]

Bao Xiaoyi, Jiang Xiaotong, Wang Zhongqing, et al. Cross—lingual aspect—level sentiment classification with graph neural network[J]. Journal of Software, 2023, 34(2): 676-689(in Chinese).

[10]

Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems(NeurIPS 2017). Long Beach,USA, 2017: 6000-6010.

[11]

Devlin J, Chang M W, Lee K, et al. BERT:Pre—training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis,USA, 2019: 4171-4186.

[12]

Li X, Bing L D, Zhang W X, et al. Exploiting BERT for end—to—end aspect—based sentiment analysis[C]// Proceedings of the 5th Workshop on Noisy User—Generated Text(W—NUT 2019). Hong Kong,China, 2019: 34-41.

[13]

Sun C, Huang L Y, Qiu X P. Utilizing BERT for aspect—based sentiment analysis via constructing auxiliary sentence[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis,USA, 2019: 380-385.

[14]

林 煌, 李弼程. 基于 BERT 模型和图注意力网络的方面级情感分析[J]. 计算机科学, 2024, 51(增 2): 240400018-7.

[15]

Lin Huang, Li Bicheng. Aspect—based sentiment analysis based on BERT model and graph attention network[J]. Computer Science, 2024, 51(Suppl 2): 240400018-7(in Chinese).

[16]

Sengupta P S, Sarkar S, Das D. HIJLI_JU at SemEval—2024 Task 7:Enhancing quantitative question answering using fine—tuned BERT models[C]// Proceedings of the 18th International Workshop on Semantic Evaluation(SemEval—2024). Mexico City,Mexico, 2024: 279-284.

[17]

Peng H Y, Xu L, Bing L D, et al. Knowing what,how and why:A near complete solution for aspect—based sentiment analysis[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York,USA, 2020: 8600-8607.

[18]

Wan H, Yang Y F, Du J F, et al. Target—aspect—sentiment joint detection for aspect—based sentiment analysis[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York,USA, 2020: 9122-9129.

[19]

Cai H J, Xia R, Yu J F. Aspect—category—opinion—sentiment quadruple extraction with implicit aspects and opinions[C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021: 340-350.

[20]

Zhang W X, Deng Y, Li X, et al. Aspect sentiment quad prediction as paraphrase generation[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Punta Cana,Dominican Republic, 2021: 9209-9219.

[21]

Hu M T, Wu Y K, Gao H, et al. Improving aspect sentiment quad prediction via template—order data augmentation[C]// Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Abu Dhabi,United Arab Emirates, 2022: 7889-7900.

[22]

Gou Z B, Guo Q Y, Yang Y J. MvP:Multi—view prompting improves aspect sentiment tuple prediction[C]// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Toronto,Canada, 2023: 4380-4397.

[23]

Zhang W X, Li X, Deng Y, et al. Towards generative 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: 504-510.

基金资助

国家自然科学基金资助项目(62337001)

AI Summary AI Mindmap
PDF (1113KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉