Performance evaluation of English to Sanskrit machine translation system
by Vimal Mishra; R.B. Mishra
International Journal of Computer Aided Engineering and Technology (IJCAET), Vol. 4, No. 4, 2012

Abstract: The performance evaluation of machine translation (MT) has proven to be a very difficult problem. In present times, the automatic evaluation methods of MT have become very popular viz. bilingual evaluation understudy (BLEU), unigram precision, unigram recall, F-measure and METEOR score. The BLEU is a metric based on n-gram co-occurrence; precision, recall and F-measure are based on unigram matches; while METEOR score is based on explicit word-to-word matches between the translation and a reference translation (human judgement). In this paper, we evaluate our English to Sanskrit MT (EST) system with these evaluation methods of MT and propose a weighted BLEU, weighted unigram precision, weighted unigram recall, weighted F-measure and weighted METEOR score that is based on assignment of weight to different part-of-speech (POS) in the translation and a reference translation. Our proposed methods of above weighted methods of MT evaluations improve the score of these evaluation methods of MT. The performance results of our EST system, with and without weight of the above methods of MT evaluations, are shown using table.

Online publication date: Sat, 16-Aug-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Aided Engineering and Technology (IJCAET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com