The purpose of this study is to address the issue of context-sensitive spelling errors in English papers. English spelling mistakes fall into two categories: non-word errors and context-sensitive errors. Context-sensitive spelling errors are more difficult to correct because it is necessary to understand the relationship between the word that needs to be changed and the context in which it is used. Non-word spelling errors are easy to fix because they can only be found by comparing the words in sentences with those in a dictionary. In any field that employs text data, spelling mistakes are regarded as noise, and document correction during preprocessing is required to reduce this issue. Context-sensitive spelling mistakes include cross-word boundary errors, typographical errors, grammatical errors, and homophone errors (which result from the incorrect use of words that sound similar but are spelled differently). Typographical errors are caused by pressing the wrong key on a keyboard (which arise from incorrect spacing between words). The emphasis of this study is typographical mistakes. The deep learning approach, which is not a currently used statistical method, is used to tackle the context-sensitive spelling mistake problem. Correction based on word embedding information, contextual embedding information, an auto-regressive (AR) language model, and an auto-encoding (AE) language model are the four components of the deep learning language model-based correction technique. The AE language model-based technique had the best correction performance in our investigation, and we confirmed its performance with a thorough corrective test. final year project is based on IEEE Paper.this will be one of the best Final year engineering project for computer science. Components that we will provide are.
1.complete documentation support
2.complete working hardware/software implemented in students environment 3.classes will held accordingly.