Difference between revisions of "Machine Translation"
From Cohen Courses
Jump to navigationJump to searchPastStudents (talk | contribs) |
PastStudents (talk | contribs) |
||
| Line 9: | Line 9: | ||
* '''Rule-based''', which includes transfer-based, interlingual, and dictionary-based translations | * '''Rule-based''', which includes transfer-based, interlingual, and dictionary-based translations | ||
* '''Statistical''', which generates translations by using statistical methods on bilingual corpora | * '''Statistical''', which generates translations by using statistical methods on bilingual corpora | ||
| − | * '''Example Based''', | + | * '''Example Based''', essentially translation by analogy |
* '''Hybrid''', combines aspects of both rule-based and statistical machine translation | * '''Hybrid''', combines aspects of both rule-based and statistical machine translation | ||
Revision as of 20:58, 29 September 2010
Summary
Machine Translation (or MT for short) is a task in the field of computational linguistics which looks at translating some input in one natural language, in the form of text or speech, into another natural language with computer software.
Common Approaches
Some common approaches to Machine Translation include the following:
- Rule-based, which includes transfer-based, interlingual, and dictionary-based translations
- Statistical, which generates translations by using statistical methods on bilingual corpora
- Example Based, essentially translation by analogy
- Hybrid, combines aspects of both rule-based and statistical machine translation
