Machine translation (MT) is the field of translating from one source language to another target language. Machine translation is one of the most dominant emerging fields in the world today. Machine translation originated in the early 1940s, during the Cold War, when there was a great need to decipher or decipher the exchange of secretly coded messages between English and Russian. At the time, the technology was called “cryptographic science.” TM is the key to the success of any new service. Nowadays, many IT and other private sectors are converging on MT technology to enhance their existing product services. This promoted the development of many new models and resulted in the development of an open source statistical machine translation (SMT) system Moses which is deployed in various institutes, research projects, etc. There are different approaches to machine translation. Say no to plagiarism. Get Custom Essay on “Why Violent Video Games Should Not Be Banned”?Get Original Essay No Author GivenRule-Based Machine Translation (RBSMT) is one of the most fundamental and oldest approaches to automatic translation. In RBSMT, we have to develop and manage rules using different grammatical conventions, lexicon and we have to process the rules [1]. Typically, the rules are coded by a language expert who has greater expertise in that area. The advantages of RBMT are that it is very simple and can be easily extended to handle any situation. There are different approaches to RBMT. These are transfer-based RBMT, Interlingua-based RBMT, and dictionary-based RBMT. One of the limitations of RBMT is that we humans have to create rules for each parsing and generation step, which is a very heavy and sometimes tedious task. We must create and develop rules in order to adapt to the new changing environment. Thus, we used the corpus-based approach due to the failure of rule-based approaches. This may be due to the increasing availability of machine-readable text and the increasing capacity of hardware. There are different approaches using corpus-based TM. They are mentioned as follows: 1.2.3.4.5. Examples: Machine translation based on statistical machine translation Statistical machine translation based on sentences Statistical machine translation based on trees Neural-based machine translation Example-based machine translation (EBMT) is one of the SMT approaches based on 'analogy. It also relies on the Bilingual Corpus as its main knowledge base [1]. Given a new test source sentence and their corresponding reference sentences, it is translated using examples or analogies from the knowledge base. The translated sentences are stored in the knowledge base. This avoids the effort of translating each new test sentence. One limitation of this approach is that if there is an unmatched test phrase, then it must be regenerated from scratch. It cannot use nearby phrases or words to predict the translation [1, 10]. Statistical machine translation (SMT) is a data- or corpus-based approach to MT. It used the supervised and unsupervised technique of machine learning algorithm to train the translation model. The objective of the SMT system is to produce a target translated sentence from a given source sentence. Among all possible candidate translation sentences for an input sentence.