A Novel Approach for Detecting Defective Expressions in Turkish

Authors : Atilla SUNCAK, Özlem AKTAŞ

Pages : 35-40

View : 19 | Download : 6

Publication Date : 2021-08-30

Article Type : Research Paper

Abstract :The use of machine learning has been increasing rapidly in recent years by being more efficient in comparison to rule-based techniques. However, NLP insert ignore into journalissuearticles values(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 insert ignore into journalissuearticles values(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.
Keywords : Conv1D, defective expressions, deep learning, NLP, semantic ambiguities, Turkish