Identifying Categories of Zones in Scientific Papers based on Lexical and Syntactical Features

Scientific papers are continually increasing on the web and it is mandatory for the researchers to grasp on some powerful tools which are helpful in an efficient process of large amounts of data. Zone identification is a Natural Language Processing application which is to classify the sentences of scientific papers into a fixed set of zone categories.In this paper, we will propose an algorithm to identify some categories of zones in scientific papers. Regarding this, we make use of some significant lexical and syntactical features of the sentences standing for these categories in a particular way. In this respect, a sequence of sentences has been used. Experimental results show that these features are capable enough to identify the desired categories in a reasonable manner.