Pooja Malik

Work place: Gautam Buddha University, Greater Noida, India-201308

E-mail: singh.pooja902@gmail.com


Research Interests: Natural Language Processing


Pooja Malik received her M. Tech (Computer Science and Engineering) degree from Banasthali University, Rajasthan, India and B. Tech (Computer Science and Engineering) degree from Uttar Pradesh Technical University, Lucknow, India. Currently, she is a research scholar at the School of Information and Communication Technology, Gautam Buddha University, Greater Noida, India. Her research interests include Natural Language Processing, Machine Translation and Machine Translation Evaluation.

Author Articles
Performance Enhancement of Machine Translation Evaluation Systems for English – Hindi Language Pair

By Pooja Malik Anurag Singh Baghel

DOI: https://doi.org/10.5815/ijmecs.2019.02.06, Pub. Date: 8 Feb. 2019

Machine Translation (MT) is a programmed conversion in which computer software is utilized to convert manuscripts from one Natural Language (like English) to a different Language (such as Hindi). To process any such conversion, through human or through automatic means, the conversion must be established such that it reinstate the complete sense of a manuscript from its base (source) linguistic into the target language. In this paper, the study of prevailing evaluation systems along with assessing their performance is achieved through the similarity metrics. Moreover, the authors have also presented an improved technique of translation employing features of Natural Language Processing and consequently, to acquire an enhanced and more accurate assessing Machine Translation system, a corpus is selected and the outcomes are compared with the prevailing methods. Besides this, two well-known systems such as Google and Bing decoders are selected to inquire and to assess the study of metrics called similarity metrics through Assessment of Text Essential Characteristics score. This is found to provide more accuracy than prevailing methods. Furthermore, evaluations are tested under various metrics systems like Jaccard similarity metrics, cosine similarity metrics, and sine metrics to deliver enhanced accuracy than prevailing methods.

[...] Read more.
Other Articles