I have customer review texts. The data consists of the the raw and manually corrected texts of the reviews. I have aligned these pairs by using similarity algorithms and matched the words on them. Since there are some mis-matched words pairs, I have eliminated the pairs under a threshold value for their counts.

Now there are raw and corrected word pairs. What kind of machine learning model can I build for spellcheck by using the data mentioned as well?



You must log in to answer this question.

Browse other questions tagged .