References
Wang W, Pan S J, Dahlmeier D, et al. Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, 2017. 3316–3322
Li X, Bing L, Li P, et al. Aspect term extraction with history attention and selective transformation. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, 2018. 4194–4200
Xu H, Liu B, Shu L, et al. Double embeddings and CNN-based sequence labeling for aspect extraction. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, 2018. 2: 592–598
Peters M E, Neumann M, Zettlemoyer L, et al. Dissecting contextual word embeddings: architecture and representation. In: Proceedings of the 2018 Conference on EMNLP, Brussels, 2018. 1499–1509
Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, 2017. 4700–4708
Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw, 2005, 18: 602–610
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems, Long Beach, 2017. 5998–6008
Pontiki M, Galanis D, Papageorgiou H, et al. Semeval-2016 task 5: aspect based sentiment analysis. In: Proceedings of the 10th International Workshop on Semantic Evaluation, San Diego, 2016. 19–30
Pontiki M, Galanis D, Papageorgiou H, et al. Semeval-2014 task 4: aspect based sentiment analysis. In: Proceedings of the 9th International Workshop on Semantic Evaluation, Dublin, 2015. 27–35
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant No. 61433015).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Conclusion
We present a densely-connected neural network for the aspect term extraction task. It enables preserving feature information from the bottommost layer to the uppermost layer in deep neural networks. The experiment results on two standard benchmark ABSA datasets indicate that our model improves ATE performances and leads to new advanced results.
Rights and permissions
About this article
Cite this article
Chen, C., Wang, H., Zhu, Q. et al. Densely-connected neural networks for aspect term extraction. Sci. China Inf. Sci. 65, 169103 (2022). https://doi.org/10.1007/s11432-019-2775-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-019-2775-9