Skip to main content
Springer Nature Link
Log in

Improving Multi-label Text Classification Models with Knowledge Graphs

  • Conference paper
  • First Online:
Service-Oriented Computing – ICSOC 2021 Workshops (ICSOC 2021)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13236))

Included in the following conference series:

  • 965 Accesses

Abstract

Multi-label Text Classification (MLTC) is a variant of classification problem where multiple labels are assigned to each instance. Most existing MLTC methods ignore the relationship between the target labels. Since the hierarchical relationship for addressing these problems is significant, a semantic network approach with the help of knowledge graphs can be used. This paper proposes a knowledge graph-based approach together with GRU (Gated Recurrent Unit) neural network model to solve an MLTC problem on a research text dataset. In particular, we leverage the Tax2Vec approach to extract hypernyms from the WordNet knowledge graph and enrich the dataset. The enrichment results in following a tree-like structure to identify the relationship between the semantic concepts. The result shows that the enriched dataset outperforms the traditional GRU neural network-based model based on different evaluation metrics.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://wordnet.princeton.edu/.

  2. 2.

    https://github.com/MohanKumarGanta/MLTC-with-KG.

  3. 3.

    https://www.kaggle.com/shivanandmn/multilabel-classification-dataset.

References

  1. Aljedani, N., Alotaibi, R., Taileb, M.: HMATC: hierarchical multi-label Arabic text classification model using machine learning. Egypt. Inform. J. 22, 225–237 (2020)

    Article  Google Scholar 

  2. Beheshti, A., Benatallah, B., Sheng, Q.Z., Schiliro, F.: Intelligent knowledge lakes: the age of artificial intelligence and big data. In: U, L.H., Yang, J., Cai, Y., Karlapalem, K., Liu, A., Huang, X. (eds.) WISE 2020. CCIS, vol. 1155, pp. 24–34. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-3281-8_3

    Chapter  Google Scholar 

  3. Beheshti, S.-M.-R., Benatallah, B., Motahari-Nezhad, H.R.: Scalable graph-based OLAP analytics over process execution data. Distrib. Parallel Databases 34(3), 379–423 (2014). https://doi.org/10.1007/s10619-014-7171-9

    Article  Google Scholar 

  4. Gargiulo, F., Silvestri, S., Ciampi, M.: Deep convolution neural network for extreme multi-label text classification. In: Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (2018)

    Google Scholar 

  5. Huang, W., et al.: Hierarchical multi-label text classification: an attention-based recurrent network approach. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1051–1060 (2019)

    Google Scholar 

  6. Jiang, X., Shen, Y., Wang, Y., Jin, X., Cheng, X.: Bakgrastec: a background knowledge graph based method for short text classification. In: 2020 IEEE International Conference on Knowledge Graph (ICKG) (2020)

    Google Scholar 

  7. Škrlj, B., Martinc, M., Kralj, J., Lavrač, N., Pollak, S.: Tax2vec: constructing interpretable features from taxonomies for short text classification. Comput. Speech Lang. 65, 101104 (2021)

    Article  Google Scholar 

  8. Pal, A., Selvakumar, M., Sankarasubbu, M.: Magnet: multi-label text classification using attention-based graph neural network. In: Proceedings of the 12th International Conference on Agents and Artificial Intelligence - vol. 2: ICAART, pp. 494–505. INSTICC, SciTePress (2020)

    Google Scholar 

  9. Pal, A., Selvakumar, M., Sankarasubbu, M.: Magnet: multi-label text classification using attention-based graph neural network. In: Proceedings of the 12th International Conference on Agents and Artificial Intelligence (2020)

    Google Scholar 

  10. Pal, A., Selvakumar, M., Sankarasubbu, M.: Multi-label text classification using attention-based graph neural network. arXiv preprint arXiv:2003.11644 (2020)

  11. Peng, H., et al.: Hierarchical taxonomy-aware and attentional graph capsule RCNNs for large-scale multi-label text classification. IEEE Trans. Knowl. Data Eng. 33, 2505–2519 (2019)

    Article  Google Scholar 

  12. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)

    Google Scholar 

  13. Sharifirad, S., Jafarpour, B., Matwin, S.: Boosting text classification performance on sexist tweets by text augmentation and text generation using a combination of knowledge graphs. In: Proceedings of the 2nd Workshop on Abusive Language Online (ALW2), pp. 107–114 (2018)

    Google Scholar 

  14. Škrlj, B., Martinc, M., Kralj, J., Lavrač, N., Pollak, S.: Tax2vec: constructing interpretable features from taxonomies for short text classification. Comput. Speech Lang. 65, 101104 (2021)

    Article  Google Scholar 

Download references

Acknowledgement

The work presented in this paper was funded by Cape Breton University (RISE grant).

Author information

Authors and Affiliations

  1. Cape Breton University, Sydney, NS, Canada

    Divya Prabhu, Enayat Rajabi, Mohan Kumar Ganta & Tressy Thomas

Authors
  1. Divya Prabhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Enayat Rajabi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohan Kumar Ganta
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tressy Thomas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Divya Prabhu .

Editor information

Editors and Affiliations

  1. Zayed University, Dubai, United Arab Emirates

    Hakim Hacid

  2. Zayed University, Abu Dhabi, United Arab Emirates

    Monther Aldwairi

  3. Deakin University, Waurn Ponds, VIC, Australia

    Mohamed Reda Bouadjenek

  4. National Research Council C.N.R., Pisa, Italy

    Marinella Petrocchi

  5. University of Lyon, Villeurbanne, France

    Noura Faci

  6. Zayed University, Dubai, United Arab Emirates

    Fatma Outay

  7. Macquarie University, Sydney, NSW, Australia

    Amin Beheshti

  8. Technical University of Berlin, Berlin, Germany

    Lauritz Thamsen

  9. Royal Melbourne Institute of Technology, Melbourne, VIC, Australia

    Hai Dong

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Prabhu, D., Rajabi, E., Ganta, M.K., Thomas, T. (2022). Improving Multi-label Text Classification Models with Knowledge Graphs. In: Hacid, H., et al. Service-Oriented Computing – ICSOC 2021 Workshops. ICSOC 2021. Lecture Notes in Computer Science, vol 13236. Springer, Cham. https://doi.org/10.1007/978-3-031-14135-5_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-14135-5_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-14134-8

  • Online ISBN: 978-3-031-14135-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics