CURRENT AND FUTURE TRENDS

NLP is still in its infancy when compared to other fields of research. One of the main reasons for that is changing the structure of texts. The structure of the text is changing day by day with the emergence of social media. Therefore, there is a need for developing new methods for processing natural language. In addition, the use of NLP in cognitive systems made NLP more complex. Cognitive computing is a field where active research is going on, and they are focusing on human-human-like interaction between human and computer. Enabling a computer think like a human is not easy, and incorporating one of the main features of humans, that is, NLP, is a tedious task. Natural language understanding, NLG, and thereby creating a natural language interaction between humans and the computer is one of the main aims of cognitive computing.

NLP relies on cognitive computing for doing NLP tasks. Introducing a cognitive approach to NLP tasks makes the NLP efficient. The influence of cognitive computing in NLP tasks. Human-like processing of natural language is made possible through bringing a cognitive approach in NLP tasks such as syntax analysis, semantic analysis, etc. One of the main areas where less research is going on is syntactic processing using the cognitive approach.

There are some areas in syntax analysis where the cognitive approach can bring a change. Human-like thinking is introduced with various strategies such as machine learning, deep learning, etc. However, it takes more time for training. Since the syntax of the language has some rules, the human thought process in syntax analysis can be mimicked easily using fuzzy logic. One of the fuzzy-based approaches for syntax analysis is predicting the kinds of sentences. That is whether the sentence is assertive, imperative, interrogative, or exclamatory. It can be done using fuzzy logic. Given a sentence as input, the probability of sentence being an assertive, declarative, interrogative, or exclamatory can be predicted using fuzzy logic combined with a knowledge base.

Another is to predict the POS tag associated with a word. There are many methods for predicting the POS tag associated with the word, but there are some words that may belong to different POS according to how they are used. Consider the word “after”; it can be an adverb, preposition, adjective, or conjunction depending on the sentence in which that word is used. The frizzy system can predict the probability of the input word being an adverb, verb, noun, preposition, adjective, pronoun, or conjunction based on the sentence.

Cognitive computing can bring a significant change in the future by making Artificial Intelligent agents more like a human (e.g., voice assistants). However, the key to achieving that is the development of more efficient NLP methodologies and tasks. Therefore, the NLP is still serving as a hot research area where researchers can contribute.

KEYWORDS

  • cognitive computing
  • neural network
  • encoder decoder network
  • RNN
  • LSTM
  • GRU

REFERENCES

  • 1. Martin, J. H., & Jurafsky, D. (2009). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Upper Saddle River, NJ, USA: Pearson Prentice-Hall.
  • 2. Clark, A. S., Fox, C„ & Lappin. S. (Eds.). (2010). The Handbook of Computational Linguistics and Natural Language Processing (p. 800). West Sussex, U.K.: Wiley-Blackwell.
  • 3. Indurkhya, N., & Damerau, F. J. (Eds.). (2010). Handbook of Natural Language Pi ocessing (Yol. 2). Boca Raton, FL, USA: CRC Press.
  • 4. Raglmnathau, K.. Lee, H., Raugarajan, S„ Chambers, N.. Surdeanu, M., Jurafsky, D., & Maiming, C. (2010. October). Amulti-pass sieve for coreference resolution. hiProceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (pp. 492-501).
  • 5. Clark, P., & Harrison, P. (2008, September). Boeing's NLP system and the challenges of semantic representation. In Proceedings of the 2008 Conference on Semantics in Text Processing (pp. 263-276).
  • 6. Manning, C., Surdeanu,M., Bauer. J., Fiukel, J„ Bethard, S., & McClosky. D. (2014). The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations (pp. 55-60).
  • 7. Berant. J., & Liang, P. (2014). Semantic parsing via paraphrasing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (Vol. l,pp. 1415-1425).
  • 8. Al-Rfou, R., & Skiena, S. (2013). SpeedRead: A fast named entity recognition Pipeline. arXiv preprint arXiv:1301.2857.
  • 9. McShane, M. (2017). Natural language understanding (NLU, not NLP) in cognitive systems. AIMagazine, 35(4), 43-56.
  • 10. Sarkar, D. (2016). Text Analytics with Python: A Practical Real-World Approach to Gaining Actionable Lnsights from your Data. New York, NY, USA: Apress.
  • 11. Khurana, D.. Koli, A., Khatter, K., & Singh, S. (2017). Natural language processing: State of the art. current trends and challenges. arXiv preprint arXiv: 170S. 05148.
  • 12. Liddy, E. D. (2001). Natural language processing.
  • 13. Young, T., Hazarika. D., Poria, S., & Cambria, E. (2018). Recent trends in deep learning- based natural language processing. IEEE Computational Intelligence Magazine, 13(3), 55-75.
  • 14. Otter, D. W„ Medina, J. R., & Kalita, J. K. (2018). A survey of the usages of deep learning in natural language processing. arXiv preprint arXiv: 1807.10854.
  • 15. Goyal, P„ Paudey. S., & Jain, K. (2018). Deep Learningfor Natural Language Pi ocessing: Cl earing Neural Networks with Python. New York, NY. USA: Apress.
  • 16. Marlabs. (2018). Cognitive Computing | A Primer (Whitepaper)
  • 17. Miller, G. A. (1995). WordNet: a lexical database for English. Communications of the ACM 35(11), 39-41.
  • 18. Baker, C. F„ Fillmore, C. J., & Lowe, J. B. (1998, August). The berkeley framenet project. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1 (pp. 86-90).
  • 19. Schuler, К. K. (2005). YerbNet: A broad-coverage, comprehensive verb lexicon.
  • 20. Kingsbury. P. R., & Palmer, M. (2002, May). From TreeBauk to PropBauk. In LREC (pp. 1989-1993).
  • 21. Liu. H.. & Singh, P. (2004). ConceptNet—a practical commonsense reasoning tool-kit. ВТ Technology' Journal, 22(4), 211-226.
  • 22. Navigli, R., & Pouzetto. S. P. (2010, July). BabelNet: Building a very large multilingual semantic network. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (pp. 216-225).
  • 23. Doug, Z., & Dong. Q. (2003, October). HowNet—a hybrid language and knowledge resource. In International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 (pp. 820-824). IEEE.
  • 24. [Online], Available: https://literarydevices.net/coherence/ on Date: 28 April 2019
  • 25. [Online], Avialable: https://www.analyticsvidhya.com
 
Source
< Prev   CONTENTS   Source