Analysing Quality of English-Hindi Machine Translation Engine Outputs Using Bayesian Classification
This work provides a domain-specific solution for improving English-Hindi machine translation quality assessment, though it appears incremental as it applies Bayesian classification to an existing problem.
The paper tackles the problem of estimating machine translation quality without human intervention by extracting 16 features from input sentences and their translations to compute a quality score using Bayesian inference from training data. The result is a method that addresses the limitation of automatic evaluation metrics, which correlate well at the corpus level but not at the sentence level.
This paper considers the problem for estimating the quality of machine translation outputs which are independent of human intervention and are generally addressed using machine learning techniques.There are various measures through which a machine learns translations quality. Automatic Evaluation metrics produce good co-relation at corpus level but cannot produce the same results at the same segment or sentence level. In this paper 16 features are extracted from the input sentences and their translations and a quality score is obtained based on Bayesian inference produced from training data.