Abstract
AbstractMachine translation (MT) is the sub-domain of natural language processing (NLP). It process and analyze natural language data which eliminates the language inconceivable matters and help to interact among people of different linguistic backgrounds. In our work, we used the statistical machine translation (SMT) approaches to comprehensively explore the translation accuracy, fluency, and adequacy with the context of low resources Indian dialect (language) Nyishi. SMT needs less training time and works well with highly complex long sentences than other methods, but it requires adequate parallel corpus, which is troublesome in the context of low-resource language like Nyishi. In this paper, we train 30,000 newly collected pairs of corpora and measured the translation accuracy in both directions forward and backward. Finally, results of individual n-gram of BLEU and NIST with and without tuning are calculated, and by using these results, we find out the effectiveness of translation accuracy in respect of fluency and adequacy.KeywordsSMTBLEU scoreHuman evaluation NISTMoses
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.