A Novel Approach for Detecting Defective Expressions in Turkish

Öz

The use of machine learning has been increasing rapidly in recent years by being more efficient in comparison to rule-based techniques. However, NLP (Natural Language Processing) operations generally require language specific solutions, especially semantic problems. Therefore, deep learning techniques are the best approach for detecting ambiguities in Turkish sentences as they do not need rule-based code implementations. Embedding word vectors are the vectorial visualizations of texts and are beneficial to analyze the word relationships in terms of semantics. In this study, CNN (Convolutional Neural Network) model is proposed to detect defective semantic expressions in Turkish sentences, and the accuracy results of the model are decided to be analyzed. This study makes a crucial contribution for Turkish in terms of semantic analysis and for further related performances.

Anahtar Kelimeler

• Conv1D
• defective expressions
• deep learning
• NLP
• semantic ambiguities
• Turkish

Kaynakça

1. [1] Ö. Aktaş, Ç.C. Birant, B. Aksu and Y. Çebi, “Automated synonym dictionary generation tool for turkish (ASDICT)”, Bilig, vol. 65, pp. 47-68, March 2013.
2. [2] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” ICLR, 2013.
3. [3] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, "Gradient-based learning applied to document recognition," In Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
4. [4] W. T. Yih, X. He, and C. Meek, “Semantic parsing for single-relation question answering,” In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol. 2, pp. 643-648, June 2014.
5. [5] Y. Shen, X. He, J. Gao, L. Deng, and G. Mesnil, “Learning semantic representations using convolutional neural networks for web search,” In Proceedings of the 23rd international conference on world wide web, 2014.
6. [6] K. Nal, G. Edward, and B. Phil, “A convolutional neural network for modelling sentences,” Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 655-665, 2014.
7. [7] R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa, “Natural language processing (almost) from scratch,” Journal of Machine Learning Research, vol. 12, pp. 2493-2537, 2011.
8. [8] F. Alessio, and A. Esuli, "An NLP approach for cross-domain ambiguity detection in requirements engineering." Automated Software Engineering, pp. 559-598, 2019

9. [9] M. Bano, "Addressing the challenges of requirements ambiguity: a review of empirical literature," IEEE Fifth International Workshop on Empirical Requirements Engineering (EmpiRE), pp. 21-24, 2015.
10. [10] Y. Hoceini, M. A. Cheragui, and M. Abbas, "Towards a new approach for disambiguation in NLP by multiple criterian decisionaid," Prague Bull. Math. Linguistics, pp. 19-32, 2011.
11. [11] M. Hussain, J.J. Bird, and D.R. Faria. “A study on cnn transfer learning for image classification,” 18th Annual UK Workshop on Computational Intelligence, UKCI, 2018.
12. [12] D. S. Dewantara, I. Budi, and M. O. Ibrohim, “3218IR at semEval-2020 task 11: conv1D and word embedding in propaganda span identification at news articles,” In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp. 1716-1721, 2020.
13. [13] K. Yoon, “Convolutional neural networks for sentence classification,” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, ‘08, 2014
14. [14] K. Radhika, K. R. Bindu, and P. Latha, “A text classification model using convolution neural network and recurrent neural network,” International Journal of Pure and Applied Mathematics, ’01, 2018, pp. 1549-1554.
15. [15] H. Mark, L. Irene, K. Spyro, and S. Toyotaro, “Medical text classification using convolutional neural networks,” Studies in Health Technology and Informatics, ‘04, 2017.
16. [16] M. Kyounghyun, P. Jaesun, J. Myeongjun, and K. Pilsung, “Text classification based on convolutional neural network with word and character level,” Journal of the Korean Institute of Industrial Engineers, ‘06, 2018, pp. 180-188.
17. [17] F. Chollet, “The sequential model,” keras.io, April 12, 2020. [Online]. Available: https://keras.io/guides/sequential_model. [Accessed July 13. 2020]