Machine translation

use of software for language translation

Machine translation, sometimes referred to by the acronym MT, is part of computational linguistics. It is the use of computer software to translate text or speech from one natural language to another.

At its basic level, MT changes words words in one natural language for words in another. That is literal translation.

Present machine translation software adapts the translation to the subject. For example, weather reports improve output by limiting the substitutions. This technique is very effective in domains where specialised formal language is used. It follows then that machine translation of government and legal documents more often produces usable output than conversation or less standardised text.

Quotes

change

In the words of the European Association for Machine Translation (EAMT):

Machine translation (MT) is the application of computers to the task of translating texts from one natural language to another. One of the very earliest pursuits in computer science, MT has proved to be an elusive goal, but today a number of systems are available which produce output which, if not perfect, is of sufficient quality to be useful in a number of specific domains.[1] (1997)

History

change

The origins of machine translation can be traced back to the work of Al-Kindi, a ninth-century Arabic cryptographer. He developed techniques for systemic language translation. He was aware of cryptanalysis, frequency analysis, probability and statistics, which are all used in modern machine translation.[2]

An idea related to machine translation appeared in the 17th century. In 1629, René Descartes proposed a universal language, where equivalent ideas shared a symbol.[3]

The idea of using digital computers for translation of natural languages was proposed in 1947 by England's A.D. Booth[4] and Warren Weaver at Rockefeller Foundation in the same year. "The memorandum written by Warren Weaver in 1949 is perhaps the single most influential publication in the earliest days of machine translation".[5][6]

Others followed. One example was reading and composing Braille texts by computer.

change

References

change
  1. "European Association for Machine Translation — What is Machine Translation?". Archived from the original on 2018-05-02. Retrieved 2018-04-24.
  2. DuPont, Quinn (January 2018). "The Cryptological Origins of Machine Translation: From al-Kindi to Weaver". Amodern. Archived from the original on 14 August 2019. Retrieved 2 September 2019.
  3. Knowlson, James (1975). Universal Language Schemes in England and France, 1600-1800. Toronto: University of Toronto Press. ISBN 0-8020-5296-7.
  4. Booth, Andrew D. (1953-05-01). "Mechanical translation". Computers and Automation 1953-05: Vol 2 Iss 4. Internet Archive. Berkeley Enterprises. p. 6.
  5. J. Hutchins (2000). "Warren Weaver and the launching of MT". Early Years in Machine Translation (PDF). Studies in the History of the Language Sciences. Vol. 97. p. 17. doi:10.1075/sihols.97.05hut. ISBN 978-90-272-4586-1. S2CID 163460375. Archived from the original (PDF) on 2020-02-28. {{cite book}}: |website= ignored (help)
  6. "Warren Weaver, American mathematician". July 13, 2020. Archived from the original on 6 March 2021. Retrieved 7 August 2020.

References

change
  1. Hutchins, W. John; and Harold L. Somers (1992). An Introduction to Machine Translation. London: Academic Press. ISBN 0-12-362830-X. Archived from the original on 2007-02-23. Retrieved 2007-08-17.

Other websites

change