方面词提取是方面级情感分析中最重要的子任务之一,其旨在从评论文本中找出意见目标。当前对于方面词提取主要使用卷积神经网络(Convolutional Neural Networks, CNN)和双嵌入的方法,但传统的CNN模型受限于卷积核感受野,不能很好地获取全局信息。为此,该文提出了一种基于双嵌入和多种注意力的方面词提取模型。联合使用non-local网络能够更好地捕获长范围依赖关系,使用与跳跃连接相结合的空间注意力能够更好地捕获文本的字符特征。该文模型在Laptop数据集和Restaurant数据集上分别进行了实验,F1值分别为83.39%和76.26%。与多个基线模型相比,该文提出的模型性能更优。
Abstract
Aspect terms extraction is the task of extracting the entity attributes commented in the opinions, which is a sub-task of aspect-based sentiment analysis. To improve the current solution base on convolutional neural networks (CNN), this paper proposes an aspect terms extraction model based on double embedding and multiple attentions. It better captures the long-range dependencies by a joint Non-local networks, betters capture the characters in the text by the spatial attention combined with jump connections. Experimented on the laptop dataset and the restaurant dataset, the proposed method achieves F1 values of 83.39% and 76.26%, respectively, better than multiple baseline models.
关键词
Non-local网络 /
空间注意力 /
方面词提取 /
跳跃连接 /
双嵌入
{{custom_keyword}} /
Key words
Non-local networks /
spatial attention /
aspect terms extraction /
jump connections /
double embedding
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Minqing Hu, Bing Liu. Mining and summarizing customer reviews [C]//Proceedings of the Tenth {ACM} {SIGKDD} International Conference on Knowledge Discovery and Data Mining, Seattle, Washington, USA, August 22-25, 2004.
[2] Guang Qiu, Bing Liu, Jiajun Bu, et al. Opinion word expansion and target extraction through double propagation[J]. Computational Linguistics, 2011, 37(1): 9-27.
[3] Qian Liu, Zhiqiang Gao, Bing Liu, et al. Automated rule selection for aspect extraction in opinion mining [C]//Proceedings of the 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina, 2015.
[4] Qiaozhu Mei, Xu Ling, Matthew Wondra, et al. Topic sentiment mixture: modeling facets and opinions in weblogs [C]//Proceedings of the 16th International Conference on World Wide Web, Banff, Alberta, Canada, 2007.
[5] He Y, Lin C, Alani H. Automatically Extracting Polarity-Bearing Topics for Cross-Domain Sentiment Classification [C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011.
[6] Chen Z, Mukherjee A, Liu B. Aspect Extraction with Automated Prior Knowledge Learning [C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014.
[7] Blei D M, Ng A Y, Jordan M I, et al. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[8] Yin Y, Wei F, Dong L, et al. Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction[J]. arXiv preprint arXiv: 1605.07843, 2016.
[9] Ming Liao, Jing Li, Haisong Zhang, et al. Coupling Global and Local Context for Unsupervised Aspect Extraction [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019.
[10] Maryna Chernyshevich. Ihs r&d belarus: Crossdomain extraction of product features using crf [C]//Proceedings of the 8th international workshop on semantic evaluation. Dublin, Ireland, 309-313, 2014.
[11] Toh Zhiqiang, Wang Wenting. DLIREC: Aspect Term Extraction and Term Polarity Classification System [C]//Proceedings of the 8th International Workshop on Semantic Evaluation, 2014.
[12] Pengfei Liu, Shafiq Joty, Helen Meng. Fine-grained opinion mining with recurrent neural networks and word embeddings [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, Lisbon, 2015.
[13] Xin Li, Wai Lam. Deep multi-task learning for aspect term extraction with memory interaction [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, 2017.
[14] Xin Li, Lidong Bing, Piji Li, et al. Aspect term extraction with history attention and selective transformation[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, Sweden, 2018.
[15] Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, et al. Coupled multi-layer attentions for coextraction of aspect and opinion terms [C]//Proceedings of the 31st Conference on Artificial Intelligence, San Francisco, California, 2017.
[16] Hu Xu, Bing Liu, Lei Shu, 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, Australia, 2018.
[17] Lei Shu, Hu Xu, Bing Liu. Controlled CNN-based sequence labeling for aspect extraction [J/OL]. arXiv preprint arXiv: 1905.06407,2019.
[18] Huaishao Luo, Tianrui Li, Bing Liu, et al. DOER: Dual Cross-Shared RNN for Aspect Term Polarity Co-Extraction [C]//Proceedings of the 57th Conference of the Association for Computational Linguistics, Florence, Italy, 2019.
[19] Xiaolong Wang, Ross Girshick, Abhinav Gupta, et al. Non-Local Neural Networks [C]//Proceedings of the Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018.
[20] Sanghyun Woo, Jongchan Park, Joon Young Lee. CBAM: Convolutional Block Attention Module [C]//Proceedings of the Computer Vision, Germany, 2018.
[21] Wang W, PanS J, Dahlmeier D, et al. Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, Austin, Texas, USA, 2016.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61462054, 61732005, 61672271, 61741112);云南省自然科学基金(2017FB098);国家博士后面上科学基金(2016M592894XB);云南省科技厅(2015FB135); 云南省重大科技项目(2018ZF017)
{{custom_fund}}
PDF(1898 KB)
