Debajyoti Chatterjee (91617007) <br/><br/>
Making neural machine reading comprehension faster 

 - MSC MI 2017-2019 
<br/><br/> This study aims at solving the Machine Reading Comprehension problem<br/>where questions have to be answered given a context passage. The challenge is<br/>to develop a computationally faster model which will have improved inference<br/>time. State of the art in many natural language understanding tasks, BERT<br/>model, has been used and knowledge distillation method has been applied to<br/>train two smaller models. The developed models are compared with other<br/>models which have been developed with the same intention. 
<br/><br/>
<br/><br/><label>Subjects--Topical Terms: </label><br/>MACHINE READING COMPREHENSION<br/>BERT MODEL<br/>NATURAL LANGUAGE PROCESSING