Suppose we have a question and a datasets of answers and human rated marks . How could we predict the marks by answer ?
My first thought is tokenize it and apply nlp . Is there a way to apply nlp that recognizes the answer is ontological to the correct answer ?
Himanshu Panwar
Software Developer - Data
You have answers(text) as features and marks to predict.
Here Latent Semantic Analysis(LSA) will help you. First do some text preprocessing on answers by removing stop words, stemming, lemmatizer. Then use tfidf or count vectorizer or word2vec to get the words score(creating feature set).
You will get matrix of numbers(scores), apply LSA (you can use SVD) on that matrix, then apply machine learning model on that feature set and score as your label and get the prediction.
Other features that might be helpful:
Cheers!!!