Design of a Morphological Generator for an English to Indian Languages in a Declension Rule-based Machine Translation System

Morphology is a branch of linguistics that deals with the internal structure of words in a natural language. Any word in a natural language is comprised of one or more morphemes. A morpheme is a smallest linguistic unit that forms a word. A morphological analyzer is a tool that analysis a given input word and outputs its internal structure along with its different morphemes. Conversely, a morphological generator creates the possible word(s) given the morphemes. This paper presents a design of a morphological generator for an English to Malayalam and English to Hindi rule-based machine translation system using declension rules. Declensions also termed as inflections are the different variations or inflected forms of a particular word in a language. Morphological generator is an essential part in the machine translation process that creates inflected words from the root word according to the morphological rules of a language. Machine translation is the branch of computational linguistics that automatically translates human language to another. The language to be translated is labeled as source language (SL) and the language into which translation is done is termed as target language (TL). The declension rule-based machine translation is accomplished by using grammar rules according to the word inflections of the target language. The proposed morphological generator module is elucidated with its framework and each of its modules and their working are expatiated in detail. The input and the output to/from the module are also illustrated using examples.