I have a task in hand where I get a dirty formed sentence and need to correct it. Examples are, "StackOverflow best question answering platform" to be converted to "StackOverflow is best question answering platform"
"John published first paper 1990" => "John published his first paper in 1990"
"John published first paper 1990" => "When did John published his first paper"
I am thinking of using a Seq2Seq / EncoderDecoder technique just like NMT and train it on the input output pairs as training data.
Can someone who is experienced at this, validate if this approach will work? or there is a better approach available?