Scribd
Upload
259 views

Machine Translation

Machine translation is the process of using computer software to translate text from one natural language to another. Scientists have attempted automated translation since computers were invented by codifying grammar rules, but this was largely unsuccessful unless the vocabulary was very limited. Modern machine translation uses either rule-based or statistical approaches, with rule-based knowing grammar but lacking fluency, and statistical having better fluency but unpredictable quality. Ambiguity of language makes full automation difficult without human maintenance of rules and vocabulary.

Uploaded by

Ioana Oltean
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
259 views

Machine Translation

Machine translation is the process of using computer software to translate text from one natural language to another. Scientists have attempted automated translation since computers were invented by codifying grammar rules, but this was largely unsuccessful unless the vocabulary was very limited. Modern machine translation uses either rule-based or statistical approaches, with rule-based knowing grammar but lacking fluency, and statistical having better fluency but unpredictable quality. Ambiguity of language makes full automation difficult without human maintenance of rules and vocabulary.

Uploaded by

Ioana Oltean
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

Machine Translation

Machine translation is automated translation. It is the process by which computer software is used to translate a text from one natural language to another. To process any translation, human or automated, the meaning of a text in the original language must be fully restored in the target language, i.e. the translation.

Scientists and academics have been trying to automate translation for almost as long as computers have been in existence. In the 1940s and 1950s it was widely assumed that once the vocabulary and the rules of grammar of a language had been codified, it would make automated translation easy, according to some researchers.

But attempts to make computers learn languages in this way were largely unsuccessful, unless the range of words they were expected to translate was very limited. Then in the 1980s, computer giant IBM carried out pioneering research into the use of words in sentences. Specifically, its researchers examined the relative frequency of different groups of three words occurring in a sentence.

Rule-Based MT
+ Out-of-domain translation quality + Knows grammatical rules + High performance and robustness + Consistency between versions - Lack of fluency - Hard to handle exceptions to rules - High development and customization costs

Statistical MT
- Poor out-of-domain quality - Does not know grammar - High CPU and disk space requirements - Inconsistency between versions + Good fluency + Good for catching exceptions to rules + Rapid and cost-effective development costs provided the required corpus exists

+ Consistent and predictable quality - Unpredictable translation quality

The main problem is that language is too complex, explains Philipp Koehn, a machine translator researcher at the University of Edinburgh School of Informatics. Language is always ambiguous, so you cant always use rules, and new vocabulary is always coming in, so you need someone to continually maintain those rules.

Disambiguation
Word-sense disambiguation concerns finding a suitable translation when a word can have more than one meaning. The problem was first raised in the 1950s by Yehoshua Bar-Hillel. He pointed out that without a "universal encyclopedia", a machine would never be able to distinguish between the two meanings of a word.

Google Translate
GT is a free translation service that provides instant translations between 65 different languages. GT works in a strange way: it doesnt translate from one language to another directly, but often translates first to English and then to the target language. But English is also ambiguous and depends of context, and this is the main source of translation errors.

BING Translator
The engine Bing Translator is running on was first developed by Yahoo!, and was known as Yahoo! Babel Fish a free web-based multilingual translation application. Yahoo! didnt sell its application to Microsoft, but simply transitioned its services to Bing Translator. This is also a statistical translation platform

1. 2. 3. 4. 5.

John Hutchins, Machine translations: problems and issues, panel at conference, 2007 Mathias Winther Madsen, The Limits of Machine Translation, 2009 http://www.bbc.co.uk http://en.wikipedia.org/wiki http://www.systransoft.com

You might also like