Marking Clause Boundary in Compound Sentences of Punjabi Language

Received: 22/Aug/2017, Revised: 08/Sep/2017, Accepted: 19/Sep/2017, Published: 30/Sep/2017 Abstract---Clause boundary identification for compound sentences in Punjabi language is one of the basic necessity for processing of compound sentences. For grammar checking of compound sentences, it is necessary to identify the structure of various independent clauses present in compound sentence. Once the sentence is identified as compound sentence, the next step is to identify its pattern. After identification of patterns, various clauses present in the sentence are extracted as it is the basic step for performing grammar checking. In this paper, author has explored a technique to identify the clause boundaries present in compound sentence. This study will be helpful in identifying and separating the compound sentences from Punjabi language corpus. Also this study will be helpful in developing other Natural Language Processing (NLP) applications like simplification compound sentence in simple sentences, Improving Machine translation system and grammar checking of compound sentences.