Machine translation
The purpose of the Wiki(pedia) Machine Translation Project is to develop ideas, methods and tools that can help translate Wikipedia articles (and Wikimedia pages) from one language to another (particularly out of English and into languages with small numbers of fluent speakers).
Motivation
Small languages can't produce articles as fast as English wikimedia projects because the number of wikipedians is too low. The solution for this problem is the translation of English wikimedia projects. But, some languages will not have enough translators. Machine Translation can improve the productivity of the community.
- But manual translation can be added later, for a more accurate text.
Approaches
Interlingua approach
A different, but related approach would be translating articles by hand into Rick Morneau's interlingua for machine translation, then writing software modules to translate automatically from that interlingua into each target language. This only saves work with respect to direct translation if there are several target languages whose modules are well enough developed, but those modules are much easier to write than full real-language to real-language automatic translation systems.
TradWiki/WikiTran
- Main article: Translation Wiki
TradWiki/WikiTran (WikipediaTranslator/WikiTranslator/BabelWiki) is a wiki that will be coded to help wikipedians translate articles from English to other languages.
Translating between closely related languages
I would imagine it would be an easier task to translate between similar languages than non-similar ones. For example, we have Wikipedias in Catalan and Spanish and Macedonian and Bulgarian, perhaps even Dutch and Afrikaans (some more studies would have to be done to evaluate which would be most appropriate). There is some free software being produced in Spain called en:Apertium that might be useful here. - FrancisTyers 21:44, 2 March 2006 (UTC)
Existing free software
- Apertium
- Apertium is an open-source platform (engine, tools) to build machine translation systems, mainly between related languages. Code, documentation, language pairs available from the Apertium website.
- Moses (Moses is licensed under the LGPL.)
- "Moses is a statistical machine translation system that allows you to automatically train translation models for any language pair. All you need is a collection of translated texts (parallel corpus)." (from their website Moses website.
- Wikipedia translation
- Tool designed to help populate smaller Wikipedias, for example translating country templates quickly
Resources:
General
- Fagan Finder Translation Wizard - single interface to many free online translators
Dictionaries
- Dutch to English Translation Tools (source available)
- English dictionary
- Ergane (free dictionary, several languages)
- WWWJDIC (English-Japanese/Japanese-English dictionary)
- Papillon project (free multilingual dictionary buillt by computational linguists)
- http://www.papillon-dictionary.org/Home.po
- Chinese, English, Estonian, French, German, Japanese, Lao, Malay, Thaï
- All Free Dictionaries Project - Dicts.info
- http://www.dicts.info/
- 37 interconnected languages - 417,521 entries - 1000+ multilingual dictionaries
- English-Chinese
- http://us.dict.cn/en/ online non-commercial English-Chinese
Code - inactive
- Linguaphile (Translator under GPL)
- http://linguaphile.sourceforge.net/
- 0.2 released in July 2002, as of June 2007 no new version released
- open source, platform independent, and programmed in perl
- simplistic and easy to use command line translator
- 56 languages
- Download code at http://www.translator.cx/dist/
- http://linguaphile.sourceforge.net/
- ===Links===
- general
- Links on Machine translation(MT): http://www.ife.dk/url-mt.htm
- Machine translation(MT), and the future of the translation industry http://accurapid.com/journal/15mt.htm
- Machine Translation: an Introductory Guide: http://clwww.essex.ac.uk/MTbook/
- Visual Interactive Syntax Learning: http://visl.sdu.dk/visl/
- wikipedia articles
- Free translations on the web
- http://anglahindi.iitk.ac.in/
- http://www.au-kbc.org/research_areas/nlp/demo/mat/(A Tamilto Hindi MT systemd eveloped in [1],Chennai)
- http://www.online-translator.com/ (PROMT free online machine translation system. Supports translation between English, Russian, Spanish, German, French, Italian and Portuguese languages)
- Portuguese
- Processamen to Computacional do Portuguiese http://www.linguateca.pt/index.html
- Meta-language
- http://www.undl.org (the new link is http://www.undlfoundation.org)A United Nations project based on an artificial, machine-readable language (UNL).
The idea is to semi-automatical lycreate a UNL textfrom, say, English,then have it fully-automatically translated in up to 150 languages on-the-fly. The project is now an independent organization.
- The World Wide Translator (The Tragedy of the Anti common softranslations memories)
- http://www.technologyreview.com/articles/01/09/wo_leo092101. asp References:
- A Word-to-Word Mode l of Translational Equivalence
Discussion
See the talk:Wikipedia Machine Translation Project page.