AllenNLP wrapper is running slow

[hunterhector]

Describe the bug
Now the allennlp wrapper runs the model on each sentence separately. This may cause the processor to be slow. For bigger models like this, we may need to implement the batch processor.

To Reproduce

Expected behavior
We need to better profile the speed to understand the expected behavior.

Screenshots
If applicable, add screenshots to help explain your problem.

Environment (please complete the following information):

• OS: [e.g. iOS]
• Version [e.g. 22]
• Python and Package verions: [e.g. Python version, Pytorch version]

Additional context
Add any other context about the problem here.