Unsupervised Technique To Conversational Machine Reading

Conversational machine reading (CMR) tools allow users to give a description of their scenario and pose a question to them [1] [2]. The CMR tool then processes the rule text in relation to the user scenario and question and either picks an appropriate answer from the set of possible answers A {Yes, No, Irrelevant} or chooses to seek futher clarification before giving an answer from the set A [3]. A number of systems [2] [3] [4] [5] have been developed with a goal to improve the precision of the answers given to the user. However, all the existing tools apply supervised learning technique which require manually labeled dataset. For every new rule text, the supervised techniques will require that a labeled dataset be created. The task of manually labeling dataset is tedious and error prone [6].