What is Apertium?
Since 2004, the Apertium project (www.apertium.org) develops a free/open-source machine translation platform, initially aimed at related-language pairs but expanded to deal with more divergent language pairs.
The mission of the Apertium project is to collaboratively develop free/open-source machine translation for as many languages as possible, and in particular:
- To give everyone free, unlimited access to the best possible machine-translation technologies.
- To maintain a modular, documented, open platform for machine translation and other human language processing tasks
- To favour the interchange and reuse of existing linguistic data.
- To make integration with other free/open-source technologies easier.
- To radically guarantee the reproducibility of machine translation and natural language processing research
The current version of the platform provides:
- a language-independent, configurable machine translation engine
- tools to manage the linguistic data necessary to build a machine translation system for a given language pair, and
- linguistic data for a growing number of language pairs (41 stable language pairs in March 2016)
Apertium’s work with lesser-resourced languages, such as Asturian, Welsh and Breton, has brought it national media exposure in Spain, the UK and France.
Apertium is used in Wikimedia Content Translation to translate Wikipedia articles. It is also one of the systems powering PLATA, the Spanish Government machine translation service, which is used also on the fly for public-service webpages.
Free/open-source software for research and business
Apertium software and data are all distributed under either version 2 or 3 of the GNU General Public License. This, on the one hand, contributes to radically reproducible machine translation research (see http://wiki.apertium.org/wiki/Publications), and allows companies such as Prompsit Language Engineering and imaxin|software to commercially offer services based on Apertium.
The Apertium community
Apertium development was initiated in 2004 by the Transducens research group at the Departament de Llenguatges i Sistemes Informàtics of the Universitat d’Alacant, as part of a joint project with the Universitat Politècnica de Catalunya, the Universidade de Vigo, Euskal Herriko Unibertsitatea, Elhuyar Foundation, imaxin|software and Eleka Ingeniaritza Linguistikoa.
Currently Apertium has more than 200 registered developers coming from these institutions and companies, or from the wider free/open-source community that has formed around it. Apertium has been selected by Google as a ‘Mentoring Organization’ for Google Summer of Code in 2009, 2010, 2011, 2012, 2013, 2014 and 2016, and Google Code-In 2010&endash;2015 where Apertium developers are paired with students, to guide them through the development of new features.
Why has Apertium joined the European Association for Machine Translation?
Even if Apertium developers come from all over the world, most of them are based in the Europe-Middle East-Northern Africa area. We in Apertium share the objectives of the EAMT, an effective platform to make machine translation known and available to everyone and to promote its development.
Links and resources
- The Apertium project: http://www.apertium.org
- Wiki: http://wiki.apertium.org
- The Apertium mailing list: https://lists.sourceforge.net/lists/listinfo/apertium-stuff
- Apertium developers meet at the #apertium Internet Relay Chat channel at freenode.net.
Francis M. Tyers, francis.tyersuit.no
Mikel L. Forcada, mlfdlsi.ua.es