Abstract
Language takes varied forms as used on different platforms. The instinctive nature of humans to use shorter message length, facilitating faster typing while maintaining semantic clarity, shapes the structure of a non-standard form of written text known as the texting language. The present work focuses on developing a Trie-based technique to model words in texting language for normalizing SMS text to Standard English text. The model is conceived and developed through systematic analysis of training data on user behaviour of texting language. Trie as a data structure is not only compact, but also is easy to manipulate for performing operations related to text normalization. Although Trie is a well-known data structure, its application to model SMS text has so far been unexplored. The results obtained using this model, despite the scheme being computationally cheap, are comparable with existing HMM based schemes that are available in the literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
91% of mobile Internet access is for social activities vs. 79% on desktops, according to Microsoft (http://www.social4retail.com/the-growth-of-mobile-marketing-and-tagging-info-graphic.html).
References
Jurafsky, D., James, H.M.: Speech & Language Processing, 2nd edn. Pearson Education, India (2000)
Kobus, C., Yvon, F., Damnati, G.: Normalizing SMS: are two metaphors better than one? In: Proceedings of the 22nd International Conference on Computational Linguistics, vol. 1, pp. 441–448. Association for Computational Linguistics (2008)
Choudhury, M., Saraf, R., Jain, V., Mukherjee, A., Sarkar, S., Basu, A.: Investigation and modeling of the structure of texting language. Int. J. Doc. Anal. Recogn. (IJDAR) 10(3–4), 157–174 (2007)
Bali, R.: A theoretical review on SMS normalization using hidden Markov models (HMMs). Int. J. Comput. Trends Technol. (IJCTT) 4(7), 2387–2388 (2013)
Grinter, R.E., Eldridge, M.A.: y do tngrs luv 2 txt msg? In: Proceedings of ECSCW, pp. 219–238. Springer, Netherlands (2001)
Pennell, D., Liu, Y.: Toward text message normalization: modeling abbreviation generation. In: Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 5364–5367 (2011)
Jose, G., Raj, N.S.: Lexical normalization model for noisy SMS text. In: First International Conference on Computational Systems and Communications (ICCSC), pp. 57–62 (2014)
Jose, G., Raj, N.S.: Noisy SMS text normalization model. In: International Conference for Convergence of Technology, pp. 1–6, (2014)
Beaufort, R., et al.: A hybrid rule/model-based finite-state framework for normalizing SMS messages. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, pp. 770–779 (2010)
Nocon, N., et al.: Norm API: an API for normalizing Filipino shortcut texts. In: Asian Language Processing (IALP), pp. 207–210. IEEE (2014)
Al-Saudi, J.: Error analysis and spelling mistakes of EFL learners at Tafila Technical University: a case study. Eur. Sci. J. 8(21), 56–75 (2013)
Acknowledgement
The author thankfully acknowledge the contribution of students Tushar Singla in conducting the experiments and preparing the draft.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chatterjee, N. (2019). A Trie Based Model for SMS Text Normalization. In: Arai, K., Bhatia, R., Kapoor, S. (eds) Intelligent Computing. CompCom 2019. Advances in Intelligent Systems and Computing, vol 997. Springer, Cham. https://doi.org/10.1007/978-3-030-22871-2_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-22871-2_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22870-5
Online ISBN: 978-3-030-22871-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)