Back close

Rule based Sentence Simplification for English to Tamil Machine Translation System

Publication Type : Journal Article

Publisher : IJCA

Source : International Journal of Computer Applications, Volume 25, Number 8, p.38-42 (2011)

Url : https://www.ijcaonline.org/archives/volume25/number8/3050-4147

Keywords : machine translation, POS tag, Sentence segmentation, Sentence simplification

Campus : Coimbatore

School : School of Engineering

Center : Computational Engineering and Networking

Department : Computer Science, Electronics and Communication

Year : 2011

Abstract : Machine translation is the process by which computer software is used to translate a text from one natural language to another but handling complex sentences by any machine translation system is generally considered to be difficult. In order to boost the translation quality of the machine translation system, simplifying an input sentence becomes mandatory. Many approaches are available for simplifying the complex sentences. In this paper, Rule based technique is proposed to simplify the complex sentences based on connectives like relative pronouns, coordinating and subordinating conjunction. Sentence simplification is expressed as the list of sub-sentences that are portions of the original sentence. The meaning of the simplified sentence remains unaltered. Characters such as („.‟,‟?‟) are used as delimiters. One of the important pre-requisite is the presence of delimiter in the given sentence. Initial splitting is based on delimiters and then the simplification is based on connectives. This method is useful as a preprocessing tool for machine translation.

Cite this Research Publication : P. C, V, D., M, Akumar, and Dr. Soman K. P., “Rule based Sentence Simplification for English to Tamil Machine Translation System”, International Journal of Computer Applications, vol. 25, pp. 38-42, 2011.

Admissions Apply Now