多特征交互的方面情感三元组提取

doi:10.3778/j.issn.1673-9418.2302077

摘要/Abstract

摘要： 方面情感三元组提取是方面级情感分析的子任务之一，旨在提取句子中的方面词、其对应的意见词和情感极性。先前研究集中于设计一种新范式以端到端的方式完成三元组提取任务。然而，这些方法忽略外部知识在模型中的作用，没有充分挖掘和利用语义信息、词性信息以及局部上下文信息。针对上述问题，提出了多特征交互的方面情感三元组提取（MFI-ASTE）模型。首先，该模型通过BERT预训练模型学习句子中的上下文语义特征信息，并使用自注意力机制加强语义特征；其次，使语义特征与所提取到的词性特征交互，二者相互学习，加强词性的组合能力与语义信息；再次，使用多个不同窗口的卷积神经网络提取每个单词的多重局部上下文特征并使用多分门控机制筛选这些多重局部特征；然后，采用双线性层融合提取到的三类外部知识特征；最后，利用双仿射注意力机制预测网格标记并通过特定的解码方案解码三元组。实验结果表明，该模型在四个数据集上的F1值比现有的主流模型分别提升了6.83%、5.60%、0.54%和1.22%。

关键词: 方面情感三元组提取, 自注意力机制, 卷积神经网络, 网格标记方案, 双仿射注意力机制

Abstract: Aspect sentiment triple extraction is one of the subtasks of aspect-level sentiment analysis, which aims to extract aspect terms, corresponding opinion terms and sentiment polarity in sentence. Previous studies focus on designing a new paradigm to complete the triplet extraction task in an end-to-end manner. They ignore the role of external knowledge in the model, thus semantic information, part-of-speech information and local context information are not fully explored and utilized. Aiming at the above problems, multi-feature interaction for aspect sentiment triplet extraction (MFI-ASTE) is proposed. Firstly, the bidirectional encoder representation from transformers (BERT) model is used to learn the context semantic feature information, meanwhile, the self-attention mechanism is used to strengthen the semantic feature. Secondly, the semantic feature interacts with the extracted part-of-speech feature and both learn from each other to strengthen the combination ability of the part-of-speech and semantic information. Thirdly, many convolutional neural networks are used to extract multiple local context features of each word, and then multi-point gate mechanism is used to filter these features. Fourthly, three features of external knowledge are fused by two linear layers. Finally, biaffine attention is used for predicting grid tagging and specific decoding schemes are used for decoding triplets. Experimental results show that the proposed model improves the F1 score by 6.83%, 5.60%, 0.54% and 1.22% respectively on four datasets compared with existing mainstream models.

Key words: aspect sentiment triplet extraction, self-attention mechanism, convolutional neural network, grid tagging scheme, biaffine attention mechanism

陈林颖, 刘建华, 郑智雄, 林杰, 徐戈, 孙水华. 多特征交互的方面情感三元组提取[J]. 计算机科学与探索, 2024, 18(4): 1057-1067.

CHEN Linying, LIU Jianhua, ZHENG Zhixiong, LIN Jie, XU Ge, SUN Shuihua. Multi-feature Interaction for Aspect Sentiment Triplet Extraction[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(4): 1057-1067.

参考文献

[1] CHEN Z, HUANG H, LIU B, et al. Semantic and syntactic enhanced aspect sentiment triplet Extraction[C]//Findings of the Association for Computational Linguistics, Aug 1-6, 2021. Stroudsburg: ACL, 2021:1474-1483.
[2] WU Z, YING C, ZHAO F, et al. Grid tagging scheme for aspect-oriented fine-grained opinion extraction[C]//Findings of the Association for Computational Linguistics, Nov 16-20, 2020. Stroudsburg: ACL, 2020: 2576-2585.
[3] 徐康, 李霏, 姬东鸿. 结合依存图卷积与文本片段搜索的方面情感三元组抽取[J]. 计算机工程, 2023, 49(4): 61-67.
XU K, LI F, JI D H. Aspect sentiment triple extraction model by combining dependency graph convolution and text span search[J]. Computer Engineering,?2023, 49(4): 61-67.
[4] XU H, LIU B, SHU L, et al. Double embeddings and CNN-based sequence labeling for aspect extraction[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Jul 15-20, 2018. Stroudsburg: ACL, 2018: 592-598.
[5] JIANG J, WANG A, AIZAWA A, et al. Attention-based relational graph convolutional network for target-oriented opinion words extraction[C]//Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 19-23, 2021. Stroudsburg: ACL, 2021: 1986-1997.
[6] LIU J, YUE Z. Attention modeling for targeted sentiment[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Apr 3-7, 2017. Stroudsburg: ACL, 2017: 572-577.
[7] TAY Y, TUAN L A, HUI S C. Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis[C]//Proceedings of the 2018 AAAI Conference on Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 5956-5963.
[8] 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 2020 AAAI Conference on Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 8600-8607.
[9] LI Y, WANG F, ZHANG W, et al. A more fine-grained aspect-sentiment-opinion triplet extraction task[J]. arXiv:2103.15255, 2021.
[10] XU L, LI H, LU W, et al. Position-aware tagging for aspect sentiment triplet extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Nov 16-20, 2020. Stroudsburg: ACL, 2020: 2339-2349.
[11] XU L, CHIA Y K, BING L. Learning span-level interactions for aspect sentiment triplet extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Aug 1-6, 2021. Stroudsburg: ACL, 2021: 4755-4766.
[12] CHEN S, WANG Y, LIU J, et al. Bidirectional machine reading comprehension for aspect sentiment triplet extraction[C]//Proceedings of the 2021 AAAI Conference on Artificial Intelligence, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 12666-12674.
[13] MAO Y, SHEN Y, YU C, et al. A joint training dual-MRC framework for aspect based sentiment analysis[C]//Proceedings of the 2021 AAAI Conference on Artificial Intelligence, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 13543-13551.
[14] LIU S, LI K, LI Z. A robustly optimized BMRC for aspect sentiment triplet extraction[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, Jul 10-15, 2022. Stroudsburg: ACL, 2022: 272-278.
[15] JIAN S Y B, NAYAK T, MAJUMDER N, et al. Aspect sentiment triplet extraction using reinforcement learning[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management, New York, Oct 30, 2021. New York: ACM, 2021: 3603-3607.
[16] ZHANG W, 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, Aug 1-6, 2021. Stroudsburg: ACL, 2021: 504-510.
[17] 夏鸿斌, 李强, 肖奕飞. 用于方面情感三元组抽取的词对关系学习方法[J]. 模式识别与人工智能, 2022, 35(3): 262-270.
XIA H B, LI Q, XIAO Y F. Word-pair relation learning method for aspect sentiment triplet extraction[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(3): 262-270.
[18] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems 26, Lake Tahoe, Dec 5-8, 2013: 3111-3119.
[19] PENNINGTON J, SOCHER R, MANNING C. GloVe: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1532-1543.
[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems?30,?Long?Beach,?Dec?4-9,?2017: 5998-6008.
[21] 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.
[22] DOZAT T, MANNING C D. Deep biaffine attention for neural dependency parsing[J]. arXiv:1611.01734, 2016.
[23] ZHANG C, REN L, MA F, et al. Structural bias for aspect sentiment triplet extraction[C]//Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Oct 12-17, 2022. Stroudsburg: ACL, 2022: 6736-6745.
[24] CHEN H, ZHAI Z, FENG F, et al. Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, May 22-27, 2022. Stroudsburg: ACL, 2022: 2974-2985.