Abstract
This submission describes the study of linguistically motivated features to estimate the translated sentence quality at sentence level on English-Hindi language pair. Several classification algorithms are employed to build the Quality Estimation (QE) models using the extracted features. We used source language text and the MT output to extract these features. Experiments show that our proposed approach is robust and producing competitive results for the DT based QE model on neural machine translation system.
Highlights
Quality Estimation (QE) is defined as a problem automatically evaluating the translation output without using the reference translations [1,2,3]
The evaluation results revealed that the DT based QE model performs better than the SVM and MLP models with all evaluation metrics i.e. Precision, Recall, F-measure and Accuracy
This paper reports our work on quality estimation task at sentence level on English-Hindi dataset
Summary
Quality Estimation (QE) is defined as a problem automatically evaluating the translation output without using the reference translations [1,2,3]. Last but not the least, filtering out the translated language sentences that are of poor quality for the purpose of post-editing by the proficient translators. With this submission we tried to address the problem as predicting the translation quality on sentence level as a discretized classification task to a single translated output corresponding to a given source sentence. In other words, using the given source language sentence and its generated translation output for feature extraction, the developed QE model is asked to label the quality to the translated sentence as Excellent or Good, or Average or Poor
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering and Advanced Technology
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.
