Research Article
Rekha: A Reference Based Machine Translation Evaluation Metric Using Linguistic Knowledge and Contextual Embeddings
@INPROCEEDINGS{10.4108/eai.24-3-2022.2319019, author={Nisheeth Joshi and Pragya Katyayan}, title={Rekha: A Reference Based Machine Translation Evaluation Metric Using Linguistic Knowledge and Contextual Embeddings }, proceedings={Proceedings of the 3rd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2022, 24-25 March 2022, New Delhi, India}, publisher={EAI}, proceedings_a={ICIDSSD}, year={2023}, month={5}, keywords={machine translation evaluation automatic evaluation mt evaluation metric linguistic evaluation word embeddings}, doi={10.4108/eai.24-3-2022.2319019} }- Nisheeth Joshi
Pragya Katyayan
Year: 2023
Rekha: A Reference Based Machine Translation Evaluation Metric Using Linguistic Knowledge and Contextual Embeddings
ICIDSSD
EAI
DOI: 10.4108/eai.24-3-2022.2319019
Abstract
Since the beginning of machine translation (MT) research, MT evaluation has been an area of interest of researchers. In literature, one can find more papers on MT evaluation than on machine translation itself. This paper describes the work done on developing our MT evaluation metric which incorporates linguistic as well as word embeddings for the evaluation of MT outputs. We have studied the performance of our metric on some English to Indian language machine translation systems. For this study, a comprehensive corpus was also developed which considered sentences based on different constructs. It was found that the proposed metric provides good results which are comparable with human (evaluation) judgments.
Copyright © 2022–2024 EAI
