Advertisement

Addressing Unseen Word Problem in Text Classification

  • Promod Yenigalla
  • Sibsambhu Kar
  • Chirag Singh
  • Ajay Nagar
  • Gaurav Mathur
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10859)

Abstract

Word based Deep Neural Network (DNN) approach of text classification suffers performance issues due to limited set of vocabulary words. Character based Convolutional Neural Network models (CNN) was proposed by the researchers to address the issue. But, character based models do not inherently capture the sequential relationship of words in texts. Hence, there is scope of further improvement by addressing unseen word problem through character model while maintaining the sequential context through word based model. In this work, we propose methods to combine both character and word based models for efficient text classification. The methods are compared with some of the benchmark datasets and state-of-the art results.

Keywords

Text classification Word embedding Character embedding Multi-channel CNN 

References

  1. 1.
    Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of EMNLP 2014 Conference, pp. 1746–1751 (2014)Google Scholar
  2. 2.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at ICLR (2013)Google Scholar
  3. 3.
    Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Proceedings of INTERSPEECH 2015, pp. 3057–3061 (2015)Google Scholar
  4. 4.
    Dai, A.M., Olah, C., Le, Q.V.: Document embedding with paragraph vectors. arXiv:1507.07998v1 [cs.CL], 29 July 2015
  5. 5.
    Kim, Y., Jernite, Y., Sontag, D., Rush, A.M: Character aware neural language models. arXiv:1508.06615v4 [cs.CL], 1 December 2015
  6. 6.
    Chen, T., Xu, R., He, Y., Wang, X.: Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN. Expert Syst. Appl. 72, 221–230 (2017)CrossRefGoogle Scholar
  7. 7.
    Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st ICML, Beijing, China, vol. 32, JMLR: W&CP (2014)Google Scholar
  8. 8.
    Wieting, J., Bansal, M., Gimpel, K., Livescu, K.: CHARAGRAM: Embedding Words and Sentences via Character n-grams. arXiv:1607.02789v1 [cs.CL], 10 July 2016
  9. 9.
    Wang, J., Wang, Z., Zhang, D., Yan, J.: Combining knowledge with deep convolutional neural networks for short text classification. In: Proceedings of IJCAI (2017)Google Scholar
  10. 10.
    Liang, D., Xu, W., Zhao, Y.: Combining word-level and character-level representations for relation classification of informal text: In: Proceedings of the 2nd Workshop on Representation Learning for NLP, Vancouver, Canada, pp. 43–47, 3 August 2017Google Scholar
  11. 11.
    Yiny, W., Kanny, K., Yuz, M., Schutze, H.: Comparative Study of CNN and RNN for Natural Language Processing. arXiv:1702.01923v1 [cs.CL], 7 February 2017
  12. 12.
    Mikolov, T., Karafiat, M., Burget, L., Cernoky, J.H., Khundanpur, S.: Recurrent neural network based language model. In: Proceedings of Interspeech (2010)Google Scholar
  13. 13.
    Tang, D., Qin, B., Liu, T.: Document modeling with gated recurrent neural network for sentiment classification. In: Proceedings of EMNLP 2015, pp. 1422–1432 (2015)Google Scholar
  14. 14.
    Wang, P., Xu, J., Xu, B., Liu, C., Zhang, H., Wang, F., Hao, H.: Semantic clustering and convolutional neural network for short text categorization. In: Proceedings ACL, pp. 352–357 (2015)Google Scholar
  15. 15.
    Conneau, A., Schwenk, H., Barrault, L., Lecun, Y.: Very deep convolutional networks for text classification. In: Proceedings of the 15th Conference of the European Chapter of the ACL, vol. 1, Long Papers, pp. 1107–1116 (2017)Google Scholar
  16. 16.
    Johnson, R., Zhang, T.: Convolutional neural networks for text categorization: Shallow word-level vs. deep character-level (2016). arXiv preprint: arXiv:1609.00718
  17. 17.
    Johnson, R. Zhang, T.: Supervised and semi-supervised text categorization using LSTM for region embeddings. In: Proceedings of the 33rd ICML, New York, USA (2016)Google Scholar
  18. 18.
    Zhou, C., Sun, C., Liu, Z., Lau, F.C.M.: A C-LSTM Neural Network for Text Classification. https://arxiv.org/pdf/1511.08630
  19. 19.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed Representations of Words and Phrases and their Compositionality. arXiv:1310.4546
  20. 20.
  21. 21.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS, vol. 9, pp. 249–256 (2010)Google Scholar
  22. 22.
    Liu, P., Qiu, X., Huang, X.: Recurrent Neural Network for Text Classification with Multi-Task Learning. arXiv:1605.05101v1 [cs.CL], 17 May 2016

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Promod Yenigalla
    • 1
  • Sibsambhu Kar
    • 1
  • Chirag Singh
    • 1
  • Ajay Nagar
    • 1
  • Gaurav Mathur
    • 1
  1. 1.Samsung R&D Institute IndiaBangaloreIndia

Personalised recommendations