Abstract
Few-shot text classification has been largely explored due to its remarkable few-shot generalization ability to in-domain novel classes. Yet, the generalization ability of existing models to cross-domain novel classes has seldom be studied. To fill the gap, we investigate a new task, called cross-domain few-shot text classification (XFew) and present a simple baseline that witnesses an appealing cross-domain generalization capability while retains a nice in-domain generalization capability. Experiments are conducted on two datasets under both in-domain and cross-domain settings. The results show that current few-shot text classification models lack a mechanism to account for potential domain shift in the XFew task. In contrast, our proposed simple baseline achieves surprisingly superior results in comparison with other models in cross-domain scenarios, confirming the need of further research in the XFew task and providing insights for possible directions. (The code and datasets are available at https://github.com/GeneZC/XFew).
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
Notes
- 1.
The layer is a fully connected layer armed with softmax.
- 2.
MAML can be simplified with first-order gradients, though.
- 3.
Some literature regards different scenarios in the dataset as separate domains. However, we think the domain shifts among them are not sufficiently large, so that in this work we do not consider them as different domains.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR (2015)
Bao, Y., Wu, M., Chang, S., Barzilay, R.: Few-shot text classification with distributional signatures. In: ICLR (2019)
Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. In: NeurIPS, pp. 932–938 (2000)
Casanueva, I., Temcinas, T., Gerz, D., Henderson, M., Vulic, I.: Efficient intent detection with dual sentence encoders. arXiv arXiv:2003.04807 (2020)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: ICLR (2019)
Chen, Y., Wang, X., Liu, Z., Xu, H., Darrell, T.: A new meta-baseline for few-shot learning. arXiv arXiv:2003.04390 (2020)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, vol. 70, pp. 1126–1135 (2017)
Gao, T., Han, X., Zhu, H., Liu, Z., Li, P., Sun, M., Zhou, J.: FewRel 2.0: towards more challenging few-shot relation classification. In: EMNLP/IJCNLP, no. 1, pp. 6249–6254 (2019)
Geng, R., Li, B., Li, Y., Zhu, X., Jian, P., Sun, J.: Induction networks for few-shot text classification. In: EMNLP-IJCNLP, no. 1, pp. 3902–3911 (2019)
Guo, Y., Codella, N.C.F., Karlinsky, L., Smith, J.R., Rosing, T., Feris, R.S.: A new benchmark for evaluation of cross-domain few-shot learning. arXiv arXiv:1912.07200 (2019)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP, pp. 1746–1751 (2014)
Liu, X., Eshghi, A., Swietojanski, P., Rieser, V.: Benchmarking natural language understanding services for building conversational agents. arXiv arXiv:1903.05566 (2019)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP, pp. 1412–1421 (2015)
Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. In: ICLR (2018)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP, vol. 14, pp. 1532–1543 (2014)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4077–4087 (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR, pp. 1199–1208 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)
Yu, M., et al.: Diverse few-shot text classification with multiple metrics. In: NAACL-HLT, pp. 1206–1215 (2018)
Acknowledgement
This work is supported by the National Key Research and Development Program of China (grant No. 2018YFC0831704) and Natural Science Foundation of China (grant No. U1636203).
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
Zhang, C., Song, D. (2021). A Simple Baseline for Cross-Domain Few-Shot Text Classification. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)
