Abstract
Opinion always has a target that usually appears in the form of an aspect. Thus, aspect term extraction is a fundamental subtask in opinion mining. Although deep learning models have achieved competitive results, they have neglected the effectiveness of the local context feature in extracting aspect terms. This paper proposes a simple yet effective bi-contextual convolutional neural network model to capture the local context feature. Besides, the lack of annotated training data restricts the potential of deep model performance. Thus, this paper proposes a template-driven data augmentation strategy to alleviate the influence of data insufficiency. Experimental results demonstrate that the data augmentation strategy can effectively enhance the performance of the proposed model, which outperforms the existing state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chernyshevich, M.: IHS RandD Belarus: cross-domain extraction of product features using CRF. Proc. SemEval 2014, 309–313 (2015)
Dai, H., Song, Y.: Neural aspect and opinion term extraction with mined rules as weak supervision. Proc. ACL 2019, 5268–5277 (2019)
Jakob, N., Gurevych, I.: Extracting opinion targets in a single and cross-domain setting with conditional random fields. Proc. EMNLP 2010, 1035–1045 (2010)
Kusner, M.J., Hernández-Lobato, J.M.: GANS for sequences of discrete elements with the gumbel-softmax distribution. arXiv preprint arXiv:1611.04051 (2016)
Li, X., Bing, L., Li, P., Lam, W., Yang, Z.: Aspect term extraction with history attention and selective transformation. Proc. IJCAI 2018, 4194–4200 (2018)
Li, X., Lam, W.: Deep multi-task learning for aspect term extraction with memory interaction. Proc. EMNLP 2017, 2886–2892 (2017)
Liao, M., Li, J., Zhang, H., Wang, L., Wu, X., Wong, K.F.: Coupling global and local context for unsupervised aspect extraction. Proc. EMNLP-IJCNLP 2019, 4571–4581 (2019)
Liu, B.: Sentiment analysis and opinion mining. Synthesis lectures on human language technologies pp. 1–184 (2012)
Liu, P., Joty, S., Meng, H.: Fine-grained opinion mining with recurrent neural networks and word embeddings. Proc. EMNLP 2015, 1433–1443 (2015)
Ma, D., Li, S., Wu, F., Xie, X., Wang, H.: Exploring sequence-to-sequence learning in aspect term extraction. Proc. ACL 2019, 3538–3547 (2019)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 1, 1–48 (2019)
Shu, L., Xu, H., Liu, B.: Lifelong learning CRF for supervised aspect extraction. Proc. ACL 2017, 148–154 (2017)
Toh, Z., Wang, W.: DLIREC: aspect term extraction and term polarity classification system. Proc. SemEval 2014, 235–240 (2014)
Wang, W., Pan, S.J., Dahlmeier, D., Xiao, X.: Recursive neural conditional random fields for aspect-based sentiment analysis. Proc. EMNLP 2016, 616–626 (2016)
Wang, W., Pan, S.J., Dahlmeier, D., Xiao, X.: Coupled multi-layer attentions for co-extraction of aspect and opinion terms. Proc. AAAI 2017, 3316–3322 (2017)
Wei, J.W., Zou, K.: EDA: Easy data augmentation techniques for boosting performance on text classification tasks. Proc. IJCNLP 2019, 6381–6387 (2019)
Xu, H., Liu, B., Shu, L., Yu, P.S.: Double embeddings and CNN-based sequence labeling for aspect extraction. Proc. ACL 2018, 592–598 (2018)
Yu, A.W., et al.: QANET: combining local convolution with global self-attention for reading comprehension. arXiv preprint arXiv:1804.09541 (2018)
Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. Proc. AAAI 2017, 2852–2858 (2017)
Acknowledgement
This work is supported by the National Key R&D Program of China (2018AAA0101203), the National Natural Science Foundation of China (61673403, U1611262), and the Natural Science Foundation of Guangdong Province (2018A030313703).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, C., Liu, Z., Wang, J., Zhou, Y. (2020). Template-Enhanced Aspect Term Extraction with Bi-Contextual Convolutional Neural Networks. In: Zhang, H., Zhang, Z., Wu, Z., Hao, T. (eds) Neural Computing for Advanced Applications. NCAA 2020. Communications in Computer and Information Science, vol 1265. Springer, Singapore. https://doi.org/10.1007/978-981-15-7670-6_39
Download citation
DOI: https://doi.org/10.1007/978-981-15-7670-6_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7669-0
Online ISBN: 978-981-15-7670-6
eBook Packages: Computer ScienceComputer Science (R0)