Machine translation\u00a0is becoming more and more popular, it is used as a predilect way\u00a0to complement\u00a0human\u00a0translation processes.\u00a0It can be understood as\u00a0a\u00a0form of computational linguistics and language engineering.\u00a0It is an automated process, carried out by a computer, not a human, where the\u00a0software\u00a0translates the\u00a0text or speech from one language to another.\u00a0<\/p>\n\n\n\n
Machine translation is the process in which words are mechanically substituted from one language into another one by the use of translation software. It can be described as a two-step procedure: first, the meaning of the source text is decoded, and then it is recoded in the target language. However, this is not as simple as it sounds. Making words, phrases and whole sentences comprehensive in the target language, takes more than just replacing the words. Not all words have an equivalent word in the target language, and many of them have more than one meaning. <\/p>\n\n\n\n
For this reason, the software used for machine translation is being constantly improved and updated, so translations become as accurate as possible. As an example, corpus statistical and neural techniques are being implemented to ensure improved output quality. <\/p>\n\n\n\n
Machine translation can be trained by human intervention. A concept that is growing\u00a0in popularity\u00a0is\u00a0\u201cAdaptive Machine Translation\u201d.\u00a0Adaptive MT is a new technology that allows MT systems\u00a0to learn from correction input,\u00a0almost immediately.\u00a0In this case,\u00a0training is not required, because the system learns instantly from\u00a0thepost-editor’s\u00a0corrections.\u00a0This is how it works:\u00a0when you are\u00a0translating\u00a0while\u00a0connected with the\u00a0machine\u00a0translator\u00a0system, that\u00a0system\u00a0can learn\u00a0\u00a0specific ways of\u00a0interpreting\u00a0things.\u00a0This\u00a0improves the quality of the results.\u00a0<\/p>\n\n\n\n
The two most common machine translation engines are Rule based and Statistical. They differ in the way they process and analyze content, but they are often combined in the same system, known as Hybrid MT. <\/p>\n\n\n\n
According to Hutchins,\u00a0\u201cThe dominant framework until the late 1980’s was what is now known as \u2018rule-based\u2019 machine translation (RBMT). Since then, research has been dominated by corpus-based approaches, among which the primary distinction is made between, on the one hand, statistical machine translation (SMT), based primarily on word frequency and word combinations, and on the other hand, example-based machine translation (EBMT), based on the extraction and combination of phrases (or other short parts of texts).<\/p>\n\n\n\n
Rule based\u00a0machine translation\u00a0(RBMT)\u00a0uses linguistic information about source and target languages. It is used most commonly for the creation of dictionaries and grammar programs. RBMT uses linguist rules to break down the content and produces more predictable\u00a0output for\u00a0terminology.\u00a0Rule based engines don’t\u00a0require\u00a0a bilingual corpus to create the translation system.\u00a0<\/p>\n\n\n\n
Statistical\u00a0machine translation\u00a0(SMT)\u00a0generates\u00a0translations using statistical methods\u00a0and models\u00a0based on bilingual text corpora, such as the\u00a0Canadian Hansard<\/a>\u00a0corpus or the record of the European Parliament.\u00a0Statistical engines don\u00b4t analyze text based on language rules.\u00a0Rather, they are\u00a0built by analyzing bilingual corpus. This method requires a\u00a0large\u00a0volume of bilingual content.<\/p>\n\n\n\n Example-based machine translation\u00a0is a method of machine translation\u00a0that uses\u00a0a bilingual corpus with parallel texts as its main knowledge base at run-time. It is essentially a translation by analogy and can be viewed as an implementation of a case-based reasoning approach to machine learning.\u00a0According to Hutchins, in its original conception EBMT seems to have been regarded primarily as a means of overcoming the deficiencies of RBMT systems, namely their weaknesses when translating between languages of greatly differing structures, such as English and Japanese.\u00a0<\/p>\n\n\n\n Hybrid machine translation is a method of machine translation that uses multiple machine translation approaches within a single machine translation system. It combines both rules and statistics. It has two approaches: Rules post-processed by statistics or statistics guided by rules. According to H. W. Xuan et al. (2012), \u201cHybrid machine translation (HMT) integrates the core of existing methods, including rule-based MT, statistical-based MT, and example-based MT, which makes up the deficiencies of individual MT method.\u201d <\/p>\n\n\n\n Between 2016 and 2017, more data was created than in the whole of human history prior. Since 2013, companies like Google and Microsoft started testing and developing the use of neural networks. Neural networks<\/a> are statistical learning models, that were first used in speech and image recognition technology. Neural networks enable MT engines to train themselves, through a process similar to the way the brain works: through trial and error (which is called deep learning). <\/p>\n\n\n\n So, in conclusion, machine translation is growing and big companies counting on its perfection. So, do we need machine translation? Of course, as translators this can sound a bit odd. Human translations can’t and mustn’t be replaced, because we are humans and we use language to approach each other in ways machines cannot understand. For example, emotions can’t be interpreted by machines. Regardless, MT can be particularly useful to support human translation and to accelerate processes. <\/p>\n\n\n\n https:\/\/en.wikipedia.org\/wiki\/Machine_translation<\/a><\/p>\n\n\n\n3. Example-based machine translation\u00a0<\/h4>\n\n\n\n
4. Hybrid Machine translation <\/h4>\n\n\n\n
Why machine translation matters?\u00a0 <\/h2>\n\n\n\n
References <\/h3>\n\n\n\n