Development of Hindi-Punjabi Parallel Corpus Using Existing Hindi-Punjabi Machine Translation System and Using Sentence Alignments

In this survey paper, we have taken problem of "development of Hindi-Punjabi parallel corpus using existing Hindi to Punjabi machine translation system and using sentence alignment". The alignment based on the length based technique, location based technique and lexical techniques. We will use Hindi-Punjabi machine translation system (i.e h2p.learnpunjabi.org). These tasks are need to Hindi-Punjabi parallel corpus. Sentence alignment is useful to developing Hindi-Punjabi parallel corpus and Hindi-Punjabi dictionary. The accuracy is basically depending upon the complexity of the corpus, more the complexity less the accuracy. Complexity means how to distribution of sentence in the target file. If any of these categories 1:1, 1:2, 2:1, 1:3, 3:1 sentences occur simultaneously in a paragraph. Our objective in this research paper is to developed Hindi-Punjabi parallel corpus using latest and existing techniques and method with a high accuracy and time efficiency.