Automatic Topic Labeling for Facilitating Interpretability of Online Learning Materials

  • Jun WangEmail author
  • Kanji Uchino
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11841)


To reduce the cognitive overhead of understanding and organizing online learning materials using topic models, especially for new learners not familiar with related domains, this paper proposes an efficient and effective approach for generating high-quality labels as better interpretation of topics discovered and typically visualized as a list of top terms. Compared with previous methods dependent on complicated post-processing processes or external resources, our phrase-based topic inference method can generate and narrow down label candidates more naturally and efficiently. The proposed approach is demonstrated and examined with real data in our corporate learning platform.


Topic model Interpretability Automatic topic labeling 


  1. 1.
    Bhatia, S., Lau, J.H., Baldwin, T.: Automatic labelling of topics with neural embeddings. In: Proceedings of COLING 2016, The 26th International Conference on Computational Linguistics: Technical Papers, pp. 953–963. The COLING 2016 Organizing Committee (2016).
  2. 2.
    Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.04805 (2018)Google Scholar
  3. 3.
    El-Kishky, A., Song, Y., Wang, C., Voss, C.R., Han, J.: Scalable topical phrase mining from text corpora. Proc. VLDB Endow. 8(3), 305–316 (2014)CrossRefGoogle Scholar
  4. 4.
    Lau, J.H., Grieser, K., Newman, D., Baldwin, T.: Automatic labelling of topic models. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, HLT 2011, vol. 1, pp. 1536–1545. Association for Computational Linguistics, Stroudsburg, PA, USA (2011)Google Scholar
  5. 5.
    Mei, Q., Shen, X., Zhai, C.: Automatic labeling of multinomial topic models. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2007, pp. 490–499. ACM, New York (2007).
  6. 6.
    Peters, M., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227–2237. Association for Computational Linguistics (2018).
  7. 7.
    Shang, J., Liu, J., Jiang, M., Ren, X., Voss, C.R., Han, J.: Automated phrase mining from massive text corpora. IEEE Trans. Knowl. Data Eng. 30(10), 1825–1837 (2018)CrossRefGoogle Scholar
  8. 8.
    Vilnis, L., McCallum, A.: Word representations via Gaussian embedding. ICLR abs/1412.6623 (2015)Google Scholar
  9. 9.
    Wang, J., Xiang, J., Uchino, K.: Topic-specific recommendation for open education resources. In: Li, F.W.B., Klamma, R., Laanpere, M., Zhang, J., Manjón, B.F., Lau, R.W.H. (eds.) ICWL 2015. LNCS, vol. 9412, pp. 71–81. Springer, Cham (2015). Scholar
  10. 10.
    Wang, J., Zhao, C., Uchino, K., Xiang, J.: Interactive topic model with enhanced interpretability. In: Proceedings of the 2nd Workshop on Explainable Smart Systems, EXSS 2019 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Fujitsu Laboratories of AmericaSunnyvaleUSA

Personalised recommendations