采用上下文专注机制的特定目标观点抽取

doi:10.3778/j.issn.1002-8331.2101-0043

摘要/Abstract

摘要： 针对现有的目标和观点抽取模型未能充分考虑两者的联系的问题，提出一种基于上下文专注机制的特定目标观点抽取模型。将抽取出的目标特征向量与每个位置的上下文词向量拼接构成最终的句子表示，加强目标与句子之间的交互，实现目标融合；采用上下文专注机制把注意力更多地放在目标词的周围，削弱远距离词的语义特征。提出的模型采用双向长短时记忆（bi-directional long short-term memory，BiLSTM）网络将句子编码，并提取特征。与现有模型相比，所提模型的精确率、召回率和F1值都有一定程度的提升，证明了所提算法的有效性。同时，预训练的BERT模型也被应用到当前任务中，使模型效果获得了进一步的提升。

关键词: 目标融合, 上下文专注机制, 双向长短时记忆（BiLSTM）网络, BERT模型

Abstract: Aiming at the problem that the existing target and viewpoint extraction models fail to fully consider the connection between the two, a specific target viewpoint extraction model based on contextual focus mechanism is proposed. First, it splices the extracted target feature vector with the context word vector at each location to form the final sentence representation, strengthens the interaction between the target and the sentence, and achieves target fusion; secondly, it uses the context focus mechanism to focus more attention around the target word, weakens the semantic features of distant words. The proposed model uses BiLSTM（bi-directional long short-term memory） network to encode sentences and extract features. Compared with existing models, the accuracy, recall and F1 value of the proposed model have been improved to a certain extent, which proves the effectiveness of the proposed algorithm. At the same time, the pre trained BERT model is applied in the current task to further improve the effect of the model.

Key words: target fusion, context focus mechanism, bi-directional long short-term memory（BiLSTM）, BERT model

陈聿鹏, 陈佳伟, 黄荣, 韩芳. 采用上下文专注机制的特定目标观点抽取[J]. 计算机工程与应用, 2022, 58(14): 160-166.

CHEN Yupeng, CHEN Jiawei, HUANG Rong, HAN Fang. Specific Target Viewpoint Extraction Using Context Focused Mechanism[J]. Computer Engineering and Applications, 2022, 58(14): 160-166.

参考文献

[1] 申梦绮.基于深度学习的方面级情感分析关键技术研究[D].成都：电子科技大学，2020.
SHEN M Q.Research on key technologies of aspect-level sentiment analysis based on deep learning[D].Chengdu：University of Electronic Science and Technology of China，2020.
[2] ZHU Y F，ZHANG W W，WANG D P.Joint opinion target and target-oriented opinion words extraction by BERT and IOT model[C]//2020 2nd Symposium on Signal Processing Systems，2020：120-125.
[3] WANG Y L，HE W，JIANG M H，et al.CHOpinionMiner：an unsupervised system for Chinese opinion target extraction[J].Concurrency and Computation：Practice and Experience，2020，32（7）：e5582.
[4] 赵威，林煜明，王超强，等.基于依赖联系分析的观点词对协同抽取[J].计算机科学，2020，47（8）：164-170.
ZHAO W，LIN Y M，WANG C Q，et al.Opinion word-pairs collaborative extraction based on dependency relation analysis[J].Computer Science，2020，47（8）：164-170.
[5] LI X，LAM W.Deep multi-task learning for aspect term extraction with memory interaction[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing，2017：2886-2892.
[6] QIU G，LIU B，BU J，et al.Opinion word expansion and target extraction through double propagation[J].Computational Linguistics，2011，37（1）：9-27.
[7] LIU K，XU H L，LIU Y，et al.Opinion target extraction using partially-supervised word alignment model[C]//Proceedings of IJCAI，2013：2134-2140.
[8] HU M，LIU B.Mining and summarizing customer reviews[C]//Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2004：168-177.
[9] ZHUANG L，JING F，ZHU X Y.Movie review mining and summarization[C]//Proceedings of the 15th ACM International Conference on Information and Knowledge Management，2006：43-50.
[10] 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.
[11] 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.
[12] 李洋，董红斌.基于CNN和BiLSTM网络特征融合的文本情感分析[J].计算机应用，2018，38（11）：3075-3080.
LI Y，DONG H B.Text sentiment analysis based on feature fusion of convolution neural network and bidirectional long short-term memory[J].Journal of Computer Applications，2018，38（11）：3075-3080.
[13] LECUN Y，BENGIO Y.Convolutional networks for images，speech，and time series[M]//The handbook of brain theory and neural networks.[S.l.]：MIT Press，1998：255-258.
[14] DEVLIN J，CHANG M W，LEE K，et al.BERT：pre-training of deep bidirectional transformers for language understanding[J].arxiv：1810.04805，2018.
[15] XU J，YAO T，ZHANG Y D，et al.Learning multimodal attention LSTM networks for video captioning[C]//Proceedings of the 25th ACM International Conference on Multimedia，2017：537-545.
[16] BOJANOWSKI P，GRAVE E，JOULIN A，et al.Enriching word vectors with subword information[J].Transactions of the Association for Computational Linguistics，2017，5：135-146.
[17] LAFFERTY J，MCCALLUM A，PEREIRA F C N.Conditional random fields：probabilistic models for segmenting and labeling sequence data[C]//Proceedings of ICML，2001：282-289.
[18] PONTIKI M，GALANIS D，PAVLOPOULOS J，et al.Semeval-2014 task 4：aspect based sentiment analysis[C]//8th International Workshop on Semantic Evaluation（SemEval 2014），2014.
[19] PENNINGTON J，SOCHER R，MANNING C D.Glove：global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing（EMNLP），2014：1532-1543.
[20] TANG D，QIN B，FENG X，et al.Effective LSTMs for target-dependent sentiment classification[J].arXiv：1512.
01100，2015.