Error Patterns and Analysis of Hindi Shallow Parser

Abstract

Simplification is an integral part of Machine translation, however, it still remains the most complex part of the process. A sentence in Hindi can be written in multiple ways. They can be complex sentences or simple ones. These sentences then need to be translated into English language. For this, the complex sentences need to be converted into simple sentences before being translated. This paper concerns Sentence Simplification of Complex Hindi Sentences for the Hindi shallow parser that was developed by IIIT. Complexity of a sentence can occur due to presence of clauses, multiple verbs and usage of conjunctions. So splitting the sentence works if the above mentioned properties of the sentence can be eliminated. To automate the process, a simplification algorithm has been formed. The paper shall talk about errors and patterns that have been analyzed, so as to improve the accuracy of the simplified sentence, and preserving the sense of the original sentence. General Terms Computational Linguistics, Natural Language Processing, Sentence Simplification, Shallow Parser, Translation.