YANG Ailin,WU Zhen,WANG Yi,et al.Aspect-Level Sentiment Triple Extraction based on Location Features and Semantic Segmentation[J].Journal of Chengdu University of Information Technology,2025,40(02):143-150.[doi:10.16836/j.cnki.jcuit.2025.02.004]
基于位置特征与语义分割的方面级情感三元组抽取方法
- Title:
- Aspect-Level Sentiment Triple Extraction based on Location Features and Semantic Segmentation
- 文章编号:
- 2096-1618(2025)02-0143-08
- Keywords:
- triple extraction; semantic segmentation; location coding; sentiment analysis; grid labeling
- 分类号:
- TP183
- 文献标志码:
- A
- 摘要:
- 方面情感三元抽取任务定义为识别句子中的方面术语、情感极性和意见术语。近期一种端到端的网格标注方法有效缓解了流水线框架中误差传播的问题,却忽略了字符间的位置关系以及局部上下文信息,导致模型无法充分挖掘文本中的局部情感特征,影响性能的进一步提升。针对上述问题,提出一种融合位置特征与语义分割的方面情感三元抽取模型。该模型首先通过BERT编码层学习每个单词的上下文表达,同时加入位置编码丰富模型对位置信息的感知。在此基础上,使用语义分割网络捕获字符间的局部依赖,充分建模文本的上下文信息,加强模型的局部建模能力。在Res14、Lap14、Res15和Res16标准数据集上的实验结果表明,相较于基准模型,提出模型的F1指标分别提升2.82、3.8、3.59、3.77个百分点,均取得最优性能,有效证明了所提方法的优越性。
- Abstract:
- Aspect-sentiment triple extraction task is defined as recognizing aspectual terms, sentiment polarity, and opinion terms in a sentence. Recently, researchers have proposed an end-to-end grid labeling method that effectively mitigates the problem of error propagation in pipelined approaches. However, the method ignores the positional relationship between characters and local contextual information, which results in the model not being able to fully mine the local sentiment features in the text, affecting the further improvement of performance. To address the above problems, this study proposes an aspectual sentiment Triple extraction model that fuses positional features with semantic segmentation. In this study, we first learn the contextual expression of each word through the BERT coding layer, and at the same time, we add location coding to enrich the model’s perception of location information. On this basis, the local dependencies between characters are captured using semantic segmentation network to fully model the contextual information of the text and strengthen the local modeling ability of the model. The experimental results on four standard datasets, Res14, Lap14, Res15 and Res16, show that compared with the benchmark model, the model proposed in this paper improves the F1 metrics by 2.82,3.8,3.59 and 3.77 percentage points, respectively, and all of them achieve optimal performance, which effectively proves the superiority of the method proposed in this paper.
参考文献/References:
[1] Abdu S A,Yousef A H,Salem A.Multimodal Video Sentiment Analysis Using Deep Learning Approaches,a Survey[J].Information Fusion,2021,76:204-226.
[2] Thet T T,Na J C,Khoo C S G.Aspect-based sentiment analysis of movie reviews on discussion boards[J].Journal of Information Science.2010,36(6):823-848.
[3] Liu B,Zhang L.A survey of opinion mining and sentiment analysis[M].Mining text data.Springer,Boston,MA,2012:415-463.
[4] 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(SemEval 2014),Dublin,Ireland,2014,27-35.
[5] Pontiki M,Galanis D,Papageorgiou H,et al.Semeval-2015 task 12:Aspect based sentiment analysis[C].Proceedings of the 9th international workshop on semantic evaluation(SemEval 2015).2015:486-495.
[6] Pontiki M,Galanis D,Papageorgiou H,et al.Semeval-2016 task 5:Aspect Based Sentiment Analysis[C].Proceedings of the 10th International Workshop on Semantic Evaluation(SemEval 2016).2016:19-30.
[7] Chen Z,Qian T.Bridge-based active domain adaptation for aspect term extraction[C].Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).2021:317-327.
[8] Sun K,Zhang R,Mensah S,et al.Aspect-level sentiment analysis via convolution over dependency tree[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).2019:5679-5688.
[9] Zhang C,Li Q,Song D.Aspect-based sentiment classification with aspect-specific graph convolutional networks[J].arXiv preprint arXiv:1909.03477,2019.
[10] 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.
[11] Fan Z,Wu Z,Dai X,et al.Target-oriented opinion words extraction with target-fused neural sequence labeling[C].Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).2019:2509-2518.
[12] Veyseh A P B,Nouri N,Dernoncourt F,et al.Introducing syntactic structures into target opinion word extraction with deep learning[J].arXiv preprint arXiv:2010.13378,2020.
[13] Wang W,Pan S J,Dahlmeier D,et al.Coupled multi-layer attentions for co-extraction of aspect and opinion terms[J].Proceedings of the AAAI conference on artificial intelligence.2017,31(1).
[14] Yu J,Jiang J,Xia R.Global inference for aspect and opinion terms co-extraction based on multi-task neural networks[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2018,27(1):168-177.
[15] Dai H,Song Y.Neural aspect and opinion term extraction with mined rules as weak supervision[J].arXiv preprint arXiv:1907.03750,2019.
[16] Peng H,Xu L,Bing L,et al.Knowing what,how and why:A near complete solution for aspect-based sentiment analysis[J].Proceedings of the AAAI conference on artificial intelligence.2020,34(5):8600-8607.
[17] Xu L,Chia Y K,Bing L.Learning span-level interactions for aspect sentiment triplet extraction[J].arXiv preprint arXiv:2107.12214,2021.
[18] Yu Bai Jian S,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.2021:3603-3607.
[19] Xu L,Li H,Lu W,et al.Position-aware tagging for aspect sentiment triplet extraction[J].arXiv preprint arXiv:2010.02609,2020.
[20] Wu Z,Ying C,Zhao F,et al.Grid tagging scheme for aspect-oriented fine-grained opinion extraction[J].arXiv preprint arXiv:2010.04640,2020.
[21] Kenton J D M W C,Toutanova L K.Bert:Pre-training of deep bidirectional transformers for language understanding[J].Proceedings of naacL-HLT.2019(1):2.
[22] Chen S,Wang Y,Liu J,et al.Bidirectional machine reading comprehension for aspect sentiment triplet extraction[J].Proceedings of the AAAI conference on artificial intelligence.2021,35(14):12666-12674.
[23] Dai H,Song Y.Neural aspect and opinion term extraction with mined rules as weak supervision[J].arXiv preprint arXiv:1907.03750,2019.
[24] Li X,Bing L,Li P,et al.A unified model for opinion target extraction and target sentiment prediction[J].Proceedings of the AAAI conference on artificial intelligence.2019,33(1):6714-6721.
[25] Zhang C,Ren L,Ma F,et al.Structural bias for aspect sentiment triplet extraction[J].arXiv preprint arXiv:2209.00820,2022.
[26] Li Y,Wang F,Zhong S.A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task[J].Mathematics,2023,11(14):3165.
相似文献/References:
[1]赵 乙,何 嘉.采用双注意力机制Deeplabv3+算法的服装图像分割[J].成都信息工程大学学报,2022,37(01):67.[doi:10.16836/j.cnki.jcuit.2022.01.012]
ZHAO Yi,HE Jia.Garment Image Segmentationn Using Dual Attention Mechanism Deeplabv3+ Algorithm[J].Journal of Chengdu University of Information Technology,2022,37(02):67.[doi:10.16836/j.cnki.jcuit.2022.01.012]
[2]陈春杉,李英祥,钟剑丹.一种基于图像语义分割的洪水检测方法[J].成都信息工程大学学报,2025,40(02):151.[doi:10.16836/j.cnki.jcuit.2025.02.005]
CHEN Chunshan,LI Yingxiang,ZHONG Jiandan.A Flood Detection Method based on Image Semantic Segmentation[J].Journal of Chengdu University of Information Technology,2025,40(02):151.[doi:10.16836/j.cnki.jcuit.2025.02.005]
备注/Memo
收稿日期:2023-10-15
基金项目:四川省科技计划资助项目(2023YFG0292、2021ZYD00 11); 国家社会科学基金资助项目(23BSH061); 四川省社会科学资助项目(SC21B034)
通信作者:吴震.E-mail:wzhen @cuit.edu.cn