基于互学习的多词向量融合情感分类框架

PDF(3249 KB)

中文信息学报 ›› 2022, Vol. 36 ›› Issue (7) : 164-172.

情感分析与社会计算

基于互学习的多词向量融合情感分类框架

曹柳文¹,周艳艳²,邬昌兴¹,黄兆华¹

作者信息 +

Mutual Learning Based Multiple Word Embeddings Fusion Framework for Sentiment Classification

CAO Liuwen¹,ZHOU Yanyan², WU Changxing¹, HUANG Zhaohua¹

Author information +

History +

摘要

方面级情感分类是当前的研究热点之一,其目标是自动推断文本中特定方面的情感倾向。融合多种不同类型的词向量作为基于深度学习模型的输入,在该任务上取得了较好的效果。然而,通过直接拼接或门控机制等方式融合多种不同的词向量,不能充分发挥每种词向量的作用。为了解决这个问题,该文提出了一种基于互学习的多词向量融合情感分类框架,其目的是充分利用普通词向量、领域词向量和情感词向量中的信息,提高分类的性能。具体地,首先构建以三种词向量的融合作为输入的主模型,然后分别构建三个以单一词向量作为输入的辅助模型,最后基于互学习的方式联合训练主模型和辅助模型,以达到相互促进的效果。在三个常用数据集上的实验表明,该文提出框架的性能明显好于基准方法。

Abstract

Aspect-level sentiment classification is a popular research topic with the purpose of automatically inferring the sentiment polarities of aspects in text. With the fusion of multiple word embeddings as input, models based on deep learning achieve promising performance on this task. Instead of concatenating different word embeddings, this paper proposes a multiple word embeddings fusing framework based on mutual learning, in which general word embeddings, domain-specific word embeddings and the sentiment word embeddings are combined to boost the performance. Specifically, we first construct the main model with the fusion of these three kinds of word embeddings as input, then build three auxiliary models with each single word embeddings as input, and finally jointly train the main model and three auxiliary models in a mutual learning manner. Experiments on three widespread datasets show that the performance of the proposed model is significantly better than those of benchmark methods.

导出引用

曹柳文,周艳艳,邬昌兴,黄兆华. 基于互学习的多词向量融合情感分类框架. 中文信息学报. 2022, 36(7): 164-172

CAO Liuwen,ZHOU Yanyan, WU Changxing, HUANG Zhaohua. Mutual Learning Based Multiple Word Embeddings Fusion Framework for Sentiment Classification. Journal of Chinese Information Processing. 2022, 36(7): 164-172

参考文献

[1] Zhang L, Wang S, Liu B. Deep learning for sentiment analysis: A survey[C]//Proceedings of the Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2018.
[2] Nguyen T H, Shirai K. PhraseRNN: Phrase recursive neural network for aspect-based sentiment analysis[C]//Proceedings of the EMNLP, 2015: 2509-2514.
[3] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv: 1409.0473, 2014.
[4] Zhang C, Li Q, Song D. Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the EMNLP, 2019: 4560-4570.
[5] Xu L, Bing L, Lu W, et al. Aspect sentiment classification with aspect-specific opinion spans[C]//Proceedings of the EMNLP, 2020: 3561-3567.
[6] Tang D, Wei F, Yang N, et al. Learning sentiment-specific word embedding for twitter sentiment classification[C]//Proceedings of the ACL, 2014: 1555-1565.
[7] Cai Y, Wan X. Multi-domain sentiment classification based on domain-aware embedding and attention[C]//Proceedings of the IJCAI, 2019: 4904-4910.
[8] Xu H, Liu B, Shu L, et al. Double embeddings and CNN-based sequence labeling for aspect extraction[C]//Proceedings of the ACL, 2018: 592-598.
[9] Kiela D, Wang C, Cho K. Dynamic meta-embeddings for improved sentence representations[C]//Proceedings of the EMNLP, 2018: 1466-1477.
[10] Tang D, Qin B, LIU T. Aspect level sentiment classification with deep memory network[C]//Proceedings of the EMNLP, 2016: 214-224.
[11] Wang S, Mazumder S, Liu B, et al. Target-Sensitive memory networks for aspect sentiment classification[C]//Proceedings of the ACL, 2018: 957-967.
[12] Wang Y, Huang M, Zhu X Y, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the EMNLP, 2016: 606-615.
[13] Ma D, Li S, Zhang X, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the IJCAI, 2017: 4068-4074.
[14] He R, Lee W S, Ng H T, et al. Effective attention modeling for aspect-level sentiment classification[C]//Proceedings of the COLING, 2018: 1121-1131
[15] 孙小婉, 王英,王鑫,等. 面向双注意力网络的特定方面情感分析模型[J]. 计算机研究与发展, 2019, 56(11): 2384-2395.
[16] 杜成玉, 刘鹏远. 基于螺旋注意力网络的方面级别情感分析模型[J]. 中文信息学报, 2020, 34(9): 70-77.
[17] Tang J, Lu Z, Su J, et al. Progressive self-supervised attention learning for aspect-level sentiment analysis[C]//Proceedings of the ACL, 2019: 557-566.
[18] Xue W, Li T. Aspect based sentiment analysis with gated convolutional networks[C]//Proceedings of the ACL, 2018: 2514-2523.
[19] Li X, Bing L, Lam W, et al. Transformation networks for target-oriented sentiment classification[C]//Proceedings of the ACL, 2018: 946-956.
[20] Lei Z, Yang Y, Yang M, et al. A human-like semantic cognition network for aspect-level sentiment classification[C]. Proceedings of the AAAI, 2019, 33: 6650-6657.
[21] Ma Y, Peng H, Cambria E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2018.
[22] He R, Lee W S, NG H T, et al. An interactive multi-task learning network for end-to-end aspect-based sentiment analysis[C]//Proceedings of the ACL, 2019: 504-515.
[23] Zhou J, Chen Q, Huang J X, et al. Position-aware hierarchical transfer model for aspect-level sentiment classification[J]. Information Sciences, 2020, 513(3): 1-16.
[24] Yin W, Schütze H. Learning word meta-embeddings[C]//Proceedings of the ACL, 2016: 1351-1360.
[25] Coates J, Bollegala D. Frustratingly easy meta-embedding: Computing meta-embeddings by averaging source word embeddings[C]//Proceedings of the NAACL, 2018: 194-198.
[26] Bollegala D, Bao C. Learning word meta-embeddings by autoencoding[C]//Proceedings of the COLING, 2018: 1650-1661.
[27] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint arXiv: 1503.02531, 2015。
[28] Zhang Y, Xiang T, Hospedales T M, et al. Deep mutual learning[C]//Proceedings of the CVPR. 2018: 4320-4328.
[29] Xue Q, Zhang W, Zha H. Improving domain-adapted sentiment classification by deep adversarial mutual learning[C]//Proceedings of the AAAI, 2020: 1-9.
[30] Liao B, Gao Y, Ney H. Multi-agent mutual learning at sentence-level and token-level for neural machine translation[C]//Proceedings of the EMNLP, 2020: 1715-1724.
[31] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016.
[32] Pontiki M, Galanis D, Papageorgiou H, et al. Semeval-2016 task 5: Aspect based sentiment analysis[C]//Proceedings of the International Workshop on Semantic Evaluation. 2016: 19-30.
[33] Dong L, Wei F, Tan C, et al. Adaptive recursive neural network for target-dependent Twitter sentiment classification[C]//Proceedings of the ACL, 2014: 49-54.
[34] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning research, 2014, 15(56): 1929-1958.
[35] Pennington J, Socher R, Manning C. Glove: Global vectors for word representation[C]//Proceedings of the EMNLP, 2014: 1532-1543.
[36] He R, Mcauley J. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering[C]//Proceedings of the 25th International Conference on World Wide Web, 2016: 507-517.
[37] 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.
[38] Wu C, Shi X, Chen Y, et al. Improving implicit discourse relation recognition with discourse-specific word embeddings[C]//Proceedings of the ACL, 2017: 269-274.
[39] Tang D, Qin B, Feng X, et al. Effective LSTMs for target-dependent sentiment classification[C]//Proceedings of the COLING, 2016: 3298-3307.
[40] Tang D, Qin B, Liu T. Aspect level sentiment classification with deep memory network[C]//Proceedings of the EMNLP, 2016: 214-224.
[41] Chen P, Sun Z, Bing L, et al. Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the EMNLP, 2017: 452-461.
[42] Ma D, Li S, Zhang X, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the IJCAI, 2017: 4068-4074.
[43] Su J, Tang J, Jiang H, et al. Enhanced aspect-based sentiment analysis models with progressive self-supervised attention learning[J]. Artificial Intelligence, 2021, 296: 103477.

基金

国家自然科学基金(61866012);国家重点研发计划(2018YFC0831106);江西03专项及5G项目(20212ABC03A32)

PDF(3249 KB)

1177

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

Received	Published
2021-03-13	2022-09-01
Issue Date
2022-09-01

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金