A Framework for Indonesian Grammar Error Correction

A study on automatic correction of English grammar errors based on deep learning

Grammatical error correction (GEC) is an important element in language learning. In this article, based on deep learning, the application of the Transformer model in GEC was briefly introduced. Then, in order to improve the performance of the model on GEC, it was optimized by a generative adversarial network (GAN). Experiments were conducted on two data sets. It was found that the performance of the GAN-combined Transformer model was significantly improved compared to the Transformer model. The F 0.5 value of the optimized model was 53.87 on CoNIL-2014, which was 2.69 larger than the Transformer model; the generalized language evaluation understanding (GLEU) value of the optimized model was 61.77 on JFLEG, which was 8.81 larger than that of the Transformer model. The optimized model also had a favorable correction performance in an actual English essay. The experimental results verify the reliability of the GAN-combined Transformer model on automatic English GEC, suggesting that the model can be further promoted and applied in practice.

Critical Analysis of Existing Punjabi Grammar Checker and a Proposed Hybrid Framework Involving Machine Learning and Rule-Base Criteria

An important area of research involving Artificial Intelligence (AI) is Natural Language Processing (NLP). The objective of training a machine is to imitate and manipulate text and speech of humans. Progressive research is undertaken to find connection between humans and their usage of language commonly used being referred as Natural Language. Various tools for different languages have been developed for operating the natural languages widely used by public. NLP integrates various disciplines and works cohesively for processing text, Information Retrieval, AI etc. One such tool used for checking the accuracy of a given sentence in any language is referred to as a Grammar Checker. So a Grammar checker of a particular language explores grammatical errors (if any) and provide remedial suggestions for correction of the same. Such feature is imbibed by virtue of Natural Language Processing using Computational Linguistics. We have justified the need of an emerging Machine Learning technique by critically evaluating existing Punjabi Grammar checker that was developed earlier in light of certain real time cases. This process is accomplished by critically evaluating the output of each phase and identifying the component accountable for generating maximum errors and false alarms. Based on this analysis, we have proposed a hybrid framework as an efficient way of analyzing correction in sentences. This is attainable through the said booming technique of Machine Learning explicitly using Deep Neural Networks in combination with existing rule-based approach. It's a novel approach as no work using machine learning has been done earlier in Punjabi Grammar Checker.

On the correction of errors in English grammar by deep learning

Using computer programs to correct English grammar can improve the efficiency of English grammar correction, improve the effect of error correction, and reduce the workload of manual error correction. In order to deal with and solve the problem of loss evaluation mismatch in the current mainstream machine translation, this study proposes the application of the deep learning method to propose an algorithm model with high error correction performance. Therefore, the framework of confrontation learning network is introduced to continuously improve the optimization model parameters through the confrontation training of discriminator and generator. At the same time, convolutional neural network is introduced to improve the algorithm training effect, which can make the correction sentences generated by the model generator better in confrontation. In order to verify the performance of the algorithm model, P-value, R-value, F 0.5-value, and MRR-value were selected for the comprehensive evaluation of the model performance index. The simulation results of the CoNLL-2014 test set and Lang-8 test set show that the proposed algorithm model has significant performance improvement compared with the traditional transformer method and can correct the fluency of sentences. It has good application values.