Kannada Grammar Checker Using LSTM Neural Network
Language is the most fundamental and historically normal means of communication today. Grammar plays a critical role in the excellence of a language. As individuals have already been educated throughout our existence with an accumulation of knowledge that is accrued, mastered over time with guidelines and a restriction of significance that allows us to comprehend and interact one another. But also to translate such awareness into a computer, to be capable of interpreting and classifying contextual evidence into a proper syntactical form, thereby validating that the information was in the correct form, is incredibly necessary at the current time since it is a sophisticated activity. The paper addresses the issue and asserts the advancement of such grammar verifying mechanism for the Dravidian language Kannada. Among the first account would be that the intricacy of the language poses a problem and preferring to have a rule based stance is an easier route and makes it possible to identify detected flaws competently. It takes a linguistic specialist to compile hundreds of parallel standards that are difficult to preserve. Here, a model is advocated that employs a deep learning method to train the LSTM (Long Short Term Memory) neural network trained over a massive data set to fulfill the necessary categorisation, using a context-based retention of the data attained through Word2Vec along with the TensorFlow and Keras packages. The proposed system is able to perform Grammatical Error Detection (GED) effectively.
2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE)