Skip to main content
SpringerLink
Log in

Learning refined features for open-world text classification with class description and commonsense knowledge

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

Open-world classification requires a classifier not only to classify samples of the observed classes but also to detect samples which are not suitable to be classified as the known classes. State-of-the-art methods train a feature extractor to extract features for separating known classes with limited training data. Then some strategies, such as outlier detector, are used to reject samples from unknown classes based on the feature space. However, they are prone to extract the discriminative features among known classes and cannot model comprehensive features of known classes, which causes the classification errors when detecting the samples from the unknown classes in an open world scenario. Motivated by the theory of psychology and cognitive science, we utilize both class descriptions and commonsense knowledge summarized by human to refine the discriminant features and propose a regularization strategy. The regularization is incorporated into the feature extractor, which is enabled to further improve the performance of our model in an open-world environment. Extensive experiments and visualization analysis are conducted to evaluate the effectiveness of our proposed model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6

Similar content being viewed by others

Data availability

The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.

Notes

  1. http://qwone.com/ jason/20Newsgroups/

  2. https://en.wikipedia.org/wiki/

References

  1. Feng, S., Wang, Y., Liu, L., Wang, D., Yu, G.: Attention based hierarchical lstm network for context-aware microblog sentiment classification. World Wide Web 22(1), 59–81 (2019)

    Article  Google Scholar 

  2. Hu, R., Zhu, X., Zhu, Y., Gan, J.: Robust svm with adaptive graph learning. World Wide Web 23(3), 1945–1968 (2020)

    Article  Google Scholar 

  3. Wu, X., Cai, Y., Li, Q., Xu, J., Leung, H.-F.: Combining weighted category-aware contextual information in convolutional neural networks for text classification. World Wide Web 23(5), 2815–2834 (2020)

    Article  Google Scholar 

  4. Ren, H., Cai, Y., Chen, X., Wang, G., Li, Q.: A two-phase prototypical network model for incremental few-shot relation classification. In: Proceedings of the 28th international conference on computational linguistics, pp. 1618–1629 (2020)

  5. Li, Z., Cai, Y., Tan, X., Han, G., Ren, H., Wu, X., Li, W.: Learning refined features for open-world text classification. In: Asia-Pacific Web (APWeb) and Web-Age information management (WAIM) Joint international conference on Web and Big Data, pp. 367–381. Springer (2021)

  6. Fei, G., Liu, B.: Breaking the closed world assumption in text classification. In: Proceedings of the 2016 conference of the north american chapter of the association for computational linguistics: human language technologies, pp. 506–514 (2016)

  7. Yang, H.-M., Zhang, X.-Y., Yin, F., Liu, C.-L.: Robust classification with convolutional prototype learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3474–3482 (2018)

  8. Liang, B., Li, H., Su, M., Bian, P., Li, X., Shi, W.: Deep text classification can be fooled. In: IJCAI. Proceeding of the 27th international joint conference on artificial intelligence, pp. 4208–4215 (2018)

  9. Shu, L., Xu, H., Liu, B.: Doc: Deep open classification of text documents. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp. 2911–2916 (2017)

  10. Markus, H.: Self-schemata and processing information about the self. J. Pers. Soc. Psychol. 35(2), 63 (1977)

    Article  Google Scholar 

  11. Banerjee, S.: Boosting inductive transfer for text classification using wikipedia. In: Sixth international conference on machine learning and applications (ICMLA 2007), pp. 148–153. IEEE (2007)

  12. Deng, Y., Shen, Y., Yang, M., Li, Y., Du, N., Fan, W., Lei, K.: Knowledge as a bridge: improving cross-domain answer selection with external knowledge. In: Proceedings of the 27th international conference on computational linguistics, pp. 3295–3305 (2018)

  13. Ghosal, D., Hazarika, D., Roy, A., Majumder, N., Mihalcea, R., Poria, S.: Kingdom: knowledge-guided domain adaptation for sentiment analysis. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp. 3198–3210 (2020)

  14. Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: an Open multilingual graph of general knowledge. In: Proceedings of the Thirty-first AAAI conference on artificial intelligence, pp. 444–4451 (2017)

  15. Kalchbrenner, N., Grefenstette, E., Blunsom, P., Kartsaklis, D., Kalchbrenner, N., Sadrzadeh, M., Kalchbrenner, N., Blunsom, P., Kalchbrenner, N., Blunsom, P.: A convolutional neural network for modelling sentences. In: Proceedings of the 52nd annual meeting of the association for computational linguistics, pp. 212–217. Association for Computational Linguistics (Volume 1: lon pares), pp. 655–665 (2014)

  16. Wang, G., Li, C., Wang, W., Zhang, Y., Shen, D., Zhang, X., Henao, R., Carin, L.: Joint embedding of words and labels for text classification. In: Proceedings of the 56th annual meeting of the association for computational linguistics (vol. 1: Long Papers), pp. 2321–2331 (2018)

  17. Ren, H., Zeng, Z., Cai, Y., Du, Q., Li, Q., Xie, H.: A weighted word embedding model for text classification. In: International conference on database systems for advanced applications, pp. 419–434. Springer (2019)

  18. Liu, M., Liu, L., Cao, J., Du, Q.: Co-attention network with label embedding for text classification. Neurocomputing 471, 61–69 (2022)

    Article  Google Scholar 

  19. Zhou, D.-W., Ye, H.-J., Zhan, D.-C.: Learning placeholders for open-set recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4401–4410 (2021)

  20. Perera, P., Morariu, V.I., Jain, R., Manjunatha, V., Wigington, C., Ordonez, V., Patel, V.M.: Generative-discriminative feature representations for open-set recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11814–11823 (2020)

  21. Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)

    Article  MATH  Google Scholar 

  22. Veenman, C.J., Reinders, M.J.: The nearest subclass classifier: a compromise between the nearest mean and nearest neighbor classifier. IEEE Trans. Pattern Anal. Mach. Intell. 27(9), 1417–1429 (2005)

    Article  Google Scholar 

  23. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2008)

    Article  Google Scholar 

  24. Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757–1772 (2012)

    Article  Google Scholar 

  25. Scheirer, W.J., Jain, L.P., Boult, T.E.: Probability models for open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2317–2324 (2014)

    Article  Google Scholar 

  26. Kotz, S., Nadarajah, S.: Kots 2000 extreme. Extreme value distributions: Theory and applications. world scientific (2000)

  27. Zhang, H., Patel, V.M.: Sparse representation-based open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1690–1696 (2016)

    Article  Google Scholar 

  28. Bendale, A., Boult, T.: Towards open world recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1893–1902 (2015)

  29. Bendale, A., Boult, T.E.: Towards open set deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1563–1572 (2016)

  30. Yoshihashi, R., Shao, W., Kawakami, R., You, S., Iida, M., Naemura, T.: Classification-reconstruction learning for open-set recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4016–4025 (2019)

  31. Xu, H., Liu, B., Shu, L., Yu, P.S.: Open-World Learning and Application to Product Classification. In: The World Wide Web conference, WWW 2019, pp. 3413–3419 (2019)

  32. Lin, T., Xu, H.: Deep unknown intent detection with margin loss. In: Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, pp. 5491–5496 (2019)

  33. Oza, P., Patel, V.M.: C2ae: Class conditioned auto-encoder for open-set recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2307–2316 (2019)

  34. Ren, H., Cai, Y., Zeng, Y.: Aspect-opinion sentiment alignment for cross-domain sentiment analysis (student abstract). Proceeding of the AAA1 conference on artificial intelligence, pp. 0–2 (2022)

  35. Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pp. 55–60 (2014)

  36. Schlichtkrull, M., Kipf, T.N, Bloem, P., Berg, R.v.d., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: European semantic Web conference, pp. 593–607. Springer (2018)

  37. Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1746–1751 (2014)

  38. Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR arXiv:1412.3555 (2014)

  39. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998–6008 (2017)

  40. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)

  41. Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in neural information processing systems, pp. 649–657 (2015)

  42. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)

  43. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

I am over helmed in all humbleness and gratefulness to acknowledge my depth to all those who have helped me to put these ideas, well above the level of simplicity and into something concrete.

Funding

This work was supported by National Natural Science Foundation of China (62076100), and Fundamental Research Funds for the Central Universities, SCUT (D2210010, D2200150, and D2201300), the Science and Technology Planning Project of Guangdong Province (2020B0101100002), the Hong Kong Research Grants Council (project no. PolyU11204919 and project no. C1031-18G) and an internal research grant from the Hong Kong Polytechnic University (project 1.9B0V). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Author information

Author notes

    Authors and Affiliations

    1. Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, China

      Haopeng Ren, Zeting Li, Yi Cai & Xin Wu

    2. School of Software Engineering, South China University of Technology, Guangzhou, China

      Haopeng Ren, Zeting Li, Yi Cai & Xin Wu

    3. Department of Computer Science, University of Warwick, Coventry, England

      Xingwei Tan

    Authors
    1. Haopeng Ren
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Zeting Li
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Yi Cai
      View author publications

      You can also search for this author in PubMed Google Scholar

    4. Xingwei Tan
      View author publications

      You can also search for this author in PubMed Google Scholar

    5. Xin Wu
      View author publications

      You can also search for this author in PubMed Google Scholar

    Contributions

    Haopeng Ren and Zeting Li provided the main idea of the paper, designed the methodology and creation of models, conduct the main experiments, and wrote the main manuscript text. YiCai provided the idea for the paper, conduct the experimental analysis, and gave the funding acquisition. Xingwei Tan conducted the visualization analysis and draw the picture in the paper. Xin Wu wrote the original Draft paper and conduct the experimental analysis. All authors read and approved the final manuscript.

    Corresponding author

    Correspondence to Yi Cai.

    Ethics declarations

    Competing interests

    The authors declare that they have no competing interests.

    Additional information

    Publisher’s note

    Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

    Haopeng Ren and Zeting Li contributed equally to this work.

    This article belongs to the Topical Collection: APWeb-WAIM 2021

    Guest Editors: Yi Cai, Leong Hou U, Marc Spaniol, Yasushi Sakurai

    Rights and permissions

    Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

    Reprints and permissions

    About this article

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this article

    Ren, H., Li, Z., Cai, Y. et al. Learning refined features for open-world text classification with class description and commonsense knowledge. World Wide Web 26, 637–660 (2023). https://doi.org/10.1007/s11280-022-01102-6

    Download citation

    • Received:

    • Revised:

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s11280-022-01102-6

    Keywords

    Search

    Navigation