属性级情感分类是情感分析领域中一个细粒度的情感分类任务,旨在判断文本中针对某个属性的情感极性。现有的属性级情感分类方法大多是使用同一种语言的标注文本进行模型的训练与测试,而现实中很多语言的标注文本规模并不足以训练一个高性能的模型,因此跨语言属性级情感分类是一个亟待解决的问题。跨语言属性级情感分类是指利用源语言文本的语义和情感信息对目标语言文本中包含的属性级情感进行挖掘和分类,相对于单语言的属性级情感分类任务而言,它具有更高的挑战性。该文提出了一个基于多通道BERT的跨语言属性级情感分类方法(Multi-BERT),该方法使用不同的BERT模型分别学习源语言文本和目标语言文本的语义特征,适应源语言和目标语言的语法特点,然后将多个BERT模型学习到的文本表示彼此交互,可以从中挖掘出更充分的属性级情感信息,提高跨语言属性级情感分类的性能。
Abstract
Aspect sentiment classification is a fine-grained sentiment classification task in the field of sentiment analysis, which aims to judge the sentiment polarity of a certain aspect in a text. Cross-language aspect sentiment classification refers to mining and classifying aspect sentiment contained in target language text by using semantic and sentimental information provided by source language text, which is more challenging than monolingual aspect sentiment classification task. This paper proposes a multi-channel BERT model (Multi-BERT) for cross-lingual aspect sentiment classification. This approach employs different BERT models to learn the semantic features and beyond different grammatical features in source and target language text. Then, the text representation learned by multiple BERT models are interacted with each other, in order to mine more sufficient aspect sentiment information and improve the performance of cross-lingual aspect sentiment classification.
关键词
多通道 /
跨语言 /
属性级情感分类
{{custom_keyword}} /
Key words
multi-channel /
cross-lingual /
aspect sentiment classification
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Wang Y, Huang M, Zhu X, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the EMNLP, 2016: 606-615.
[2] Wang J, Li J,Li S, et al. Aspect sentiment classification with both word-level and clause-level attention networks[C]//Proceedings of the IJCAI, 2018: 4439-4445.
[3] He R, Lee W, Ng H, et al. Effective attention modeling for aspect-level sentiment classification[C]//Proceedings of the COLING, 2018: 1121-1131.
[4] Lin P, Yang M, Lai J. Deep mask memory network with semantic dependency and context moment for aspect level sentiment classification[C]//Proceedings of the IJCAI, 2019: 5088-5094.
[5] He R, Lee W, Ng H, et al. Exploiting document knowledge for aspect-level sentiment classification[C]//Proceedings of the ACL, 2018: 579-585.
[6] Chen Z, Qian T. Transfer capsule network for aspect level sentiment classification[C]//Proceedings of the ACL, 2019: 547-556.
[7] Ma Y, Peng H, Cambria E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[C]//Proceedings of the AAAI, 2018: 5876-5883.
[8] Lambert P. Aspect-level cross-lingual sentiment classification with constrained SMT[C]//Proceedings of the Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, 2015.
[9] Barnes J, Lambert P, Badia T. Exploring distributional representations and machine translation for aspect-based cross-lingual sentiment classification[C]//Proceedings of the COLING. Osaka, Japan, 2016: 1613-1623.
[10] Chen X, Sun Y, Athiwaratkun B, et al. Adversarial deep averaging networks for cross-lingual sentiment classification[J]. Transactions of the Association for Computational Linguistics, 2018, 6: 557-570.
[11] Keung P, Lu Y, Bhardwaj V. Adversarial learning with contextual embeddings for zero-resource cross-lingual classification and NER[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China, 2019.
[12] Zhou X, Wan X, Xiao J. Attention-based LSTM network for cross-lingual sentiment classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016.
[13] Wan X. Co-training for cross-lingual sentiment classification[C]//Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP, Singapore, 2009: 235-243.
[14] Pontiki M, Galanis D, Papageorgiou H, et al. Sem-Eval-2016 task 5: aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation, 2016: 19-30.
[15] Sun C, Huang L, Qiu X. Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence[C]//Proceedings of the NAACL-HLT, 2019: 380-385.
[16] Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
[17] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[18] Tang D, Qin B, Feng X, et al. Effective LSTMS for target-dependent sentiment classification[C]//Proceedings of the COLING, 2016: 3298-3307.
[19] Zhang C, Li Q, Song D. Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 4568-4578.
[20] Lample G, Conneau A. Cross-lingual language model pretraining[C]//Proceedings of the NeurIPS, 2019:7057-7067.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62006166,62076175,62076176);中国博士后科学基金(2019M661930);江苏省高校优势学科建设工程自主项目
{{custom_fund}}
PDF(1701 KB)
