Abstract
This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain. Two natural questions are: Can the system transfer the knowledge learned in the past from the previous tasks to the new task to help it learn a better model for the new task? And, can old models for previous tasks be improved in the process as well? This paper proposes a novel technique called KAN to achieve these objectives. KAN can markedly improve the SC accuracy of both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of KAN is demonstrated through extensive experiments (Code and data are available at: https://github.com/ZixuanKe/LifelongSentClass).
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
Similar content being viewed by others
Notes
- 1.
For simplicity, we only show the process for one training example, but our actual system trains in batches.
- 2.
References
Aharoni, R., Goldberg, Y.: Morphological inflection generation with hard monotonic attention. In: ACL (2017)
Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with A-GEM. In: ICLR (2019)
Chen, Z., Liu, B.: Topic modeling using topics from many domains, lifelong learning and big data. In: ICML (2014)
Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 12(3), 1–207 (2018)
Chen, Z., Ma, N., Liu, B.: Lifelong learning for sentiment classification. In: ACL (2015)
Fernando, C., et al.: PathNet: evolution channels gradient descent in super neural networks. CoRR abs/1701.08734 (2017)
He, X., Jaeger, H.: Overcoming catastrophic interference using conceptor-aided backpropagation. In: ICLR (2018)
Kamra, N., Gupta, U., Liu, Y.: Deep generative dual memory network for continual learning. CoRR abs/1710.10368 (2017)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. CoRR (2016)
Kornell, N., Hays, M.J., Bjork, R.A.: Unsuccessful retrieval attempts enhance subsequent learning. J. Exp. Psychol. Learn. Memory Cogn. 35(4), 989 (2009)
Lange, M.D., et al.: Continual learning: a comparative study on how to defy forgetting in classification tasks. CoRR abs/1909.08383 (2019)
Lee, S., Kim, J., Jun, J., Ha, J., Zhang, B.: Overcoming catastrophic forgetting by incremental moment matching. In: NeurIPS (2017)
Liu, B.: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge University Press, Cambridge (2015)
Lopez-Paz, D., Ranzato, M.: Gradient episodic memory for continual learning. In: NeurIPS (2017)
Lv, G., Wang, S., Liu, B., Chen, E., Zhang, K.: Sentiment classification by leveraging the shared knowledge from a sequence of domains. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds.) DASFAA 2019. LNCS, vol. 11446, pp. 795–811. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-18576-3_47
Mallya, A., Lazebnik, S.: PackNet: adding multiple tasks to a single network by iterative pruning. In: CVPR (2018)
McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation. Elsevier (1989)
Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54–71 (2019)
Pontiki, M., et al.: Semeval-2016 task 5: aspect based sentiment analysis. In: SemEval (2016)
Rebuffi, S., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: CVPR (2017)
Rostami, M., Kolouri, S., Pilly, P.K.: Complementary learning for overcoming catastrophic forgetting using experience replay. In: IJCAI (2019)
Ruvolo, P., Eaton, E.: ELLA: an efficient lifelong learning algorithm. In: ICML (2013)
Seff, A., Beatson, A., Suo, D., Liu, H.: Continual learning in generative adversarial nets. CoRR abs/1705.08395 (2017)
Serrà , J., Suris, D., Miron, M., Karatzoglou, A.: Overcoming catastrophic forgetting with hard attention to the task. In: ICML (2018)
Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NeurIPS (2017)
Shu, L., Xu, H., Liu, B.: Lifelong learning CRF for supervised aspect extraction. In: ACL (2017)
Silver, D.L., Yang, Q., Li, L.: Lifelong machine learning systems: Beyond learning algorithms. In: AAAI (2013)
Wang, H., Liu, B., Wang, S., Ma, N., Yang, Y.: Forward and backward knowledge transfer for sentiment classification. In: ACML (2019)
Wang, S., Lv, G., Mazumder, S., Fei, G., Liu, B.: Lifelong learning memory networks for aspect sentiment classification. In: IEEE International Conference on Big Data, Big Data (2018)
Xia, R., Jiang, J., He, H.: Distantly supervised lifelong learning for large-scale social media sentiment analysis. IEEE Trans. Affect. Comput. 8, 480–491 (2017)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)
Zeng, G., Chen, Y., Cui, B., Yu, S.: Continuous learning of context-dependent processing in neural networks. Nat. Mach. Intell. 1, 364–372 (2019)
Acknowledgments
This work was supported in part by two grants from National Science Foundation: IIS-1910424 and IIS-1838770, and a research gift from Northrop Grumman.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ke, Z., Liu, B., Wang, H., Shu, L. (2021). Continual Learning with Knowledge Transfer for Sentiment Classification. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12459. Springer, Cham. https://doi.org/10.1007/978-3-030-67664-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-67664-3_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67663-6
Online ISBN: 978-3-030-67664-3
eBook Packages: Computer ScienceComputer Science (R0)
