Abstract
Multi-task techniques are effective for handling the problem of small size of the datasets. They can leverage additional rich information from other tasks for improving the performance of the target task. One of the problems in the multi-task based methods is which resources are proper to be utilized as the auxiliary tasks and how to select the shared structures with an effective search mechanism. We propose a novel neural-based multi-task Shared Structure Encoding (SSE) to define the exploration space by which we can easily formulate the multi-task architecture search. For the search approaches, because these existing Network Architecture Search (NAS) techniques are not specially designed for the multi-task scenario, we propose two original search approaches, i.e., m-Sparse Search approach by Shared Structure encoding for neural-based Multi-Task models (m-S4MT) and Task-wise Greedy Generation Search approach by Shared Structure encoding for neural-based Multi-Task models (TGG-S3MT). The experiments based on the real text datasets with multiple text mining tasks show that SSE is effective for formulating the multi-task architecture search. Moreover, both m-S4MT and TGG-S3MT have better performance on the target aspects than the single-task method, multi-label method, naïve multi-task methods and the variant of the NAS approach from the existing works. Especially, 1-S4MT with a sparse assumption on the auxiliary tasks has good performance with very low computation cost.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)
De Silva, P.U.K., K. Vance, C.: Preserving the quality of scientific research: peer review of research articles. Scientific Scholarly Communication. FLS, pp. 73–99. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-50627-2_6
Dong, F., Zhang, Y.: Automatic features for essay scoring - an empirical study. In: EMNLP, pp. 1072–1077 (2016)
Dong, F., Zhang, Y., Yang, J.: Attention-based recurrent convolutional neural network for automatic essay scoring. In: CoNLL, pp. 153–162 (2017)
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. 20, 1–21 (2019)
Ghosal, T., Verma, R., Ekbal, A., Bhattacharyya, P.: DeepSentiPeer: harnessing sentiment in review texts to recommend peer review decisions. In: ACL, pp. 1120–1130 (2019)
Guo, H., Pasunuru, R., Bansal, M.: Soft layer-specific multi-task summarization with entailment and question generation. In: ACL, pp. 687–697 (2018)
Hershcovich, D., Abend, O., Rappoport, A.: Multitask parsing across semantic representations. In: ACL, pp. 373–385 (2018)
Huang, J.B.: Deep paper gestalt. arXiv preprint arXiv:1812.08775 (2018)
Isonuma, M., Fujino, T., Mori, J., Matsuo, Y., Sakata, I.: Extractive summarization using multi-task learning with document classification. In: ACL, pp. 2101–2110 (2017)
Johnson, R., Zhang, T.: Deep pyramid convolutional neural networks for text classification. In: ACL, pp. 562–570 (2017)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)
Kang, D., Ammar, W., Dalvi, B., van Zuylen, M., Kohlmeier, S., Hovy, E., Schwartz, R.: A dataset of peer reviews (PeerRead): collection, insights and NLP applications. NAACL. 1, 1647–1661 (2018)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP. pp. 1746–1751 (2014)
Langford, J., Guzdial, M.: The arbitrariness of reviews, and advice for school administrators. Commun. ACM 58(4), 12–13 (2015)
Lin, Y., Yang, S., Stoyanov, V., Ji, H.: A multi-lingual multi-task architecture for low-resource sequence labeling. ACL. 1, 799–809 (2018)
Liu, H., Simonyan, K., Yang, Y.: Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
Liu, J., Chang, W.C., Wu, Y., Yang, Y.: Deep learning for extreme multi-label text classification. In: SIGIR, pp. 115–124 (2017)
Liu, P., Qiu, X., Huang, X.: Adversarial multi-task learning for text classification. In: ACL, pp. 1–10 (2017)
Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. In: ACL, pp. 4487–4496 (2019)
Lu, Y., Kumar, A., Zhai, S., Cheng, Y., Javidi, T., Feris, R.S.: Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification. In: CVPR, pp. 1131–1140 (2017)
Luan, Y., He, L., Ostendorf, M., Hajishirzi, H.: Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction. In: EMNLP, pp. 3219–3232 (2018)
McCann, B., Keskar, N., Xiong, C., Socher, R.: The natural language decathlon: multitask learning as question answering. arXiv preprint arXiv:1806:08730 (2018)
Pasunuru, R., Bansal, M.: Continual and multi-task architecture search. In: ACL, pp. 1911–1922 (2019)
Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)
Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: NIPS, pp. 525–536 (2018)
Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS, pp. 2951–2959 (2012)
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2019)
Wang, K., Wan, X.: Sentiment analysis of peer review texts for scholarly papers. In: SIGIR, pp. 175–184 (2018)
Xiong, W., Litman, D.J.: Automatically predicting peer-review helpfulness. In: ACL-HLT, pp. 502–507 (2011)
Zhang, Y., Yang, Q.: Learning sparse task relations in multi-task learning. In: AAAI, pp. 2914–2920 (2017)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: CVPR, pp. 8697–8710 (2018)
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
Li, J., Fukumoto, F. (2021). Multi-task Neural Shared Structure Search: A Study Based on Text Mining. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12682. Springer, Cham. https://doi.org/10.1007/978-3-030-73197-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-73197-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73196-0
Online ISBN: 978-3-030-73197-7
eBook Packages: Computer ScienceComputer Science (R0)