A free/open-source platform for machine translation and language technology

There are around 7,000 languages in the world today, around half of which are written. Most language technology is only available for a tiny fraction of these. Certainly under 1%. Apertium is a project which aims to help create language technology, particularly machine translation systems for the other 99%. Because most of the languages we work with have very little in the way of existing translations, we rely on making the most of all kinds of different resources from written grammars to dictionaries, corpus collections and help from native speakers and activists.

lightbulb_outline View ideas list


  • c++
  • python
  • xml
  • fsts


  • Other
  • machine translation
  • language technology
  • grammar
  • natural language processing
comment IRC Channel
email Mailing list
mail_outline Contact email

Apertium 2018 Projects

  • Marc Riera Irigoyen
    Adopting the unreleased Romanian-Catalan pair and upgrading other pairs to the monolingual module system
    Currently there are no machine translation systems offering direct translation between Romanian and Catalan available to the general public. English...
  • Anastasia Kuznetsova
    Adoption of Guarani - Spanish pair
    Guarani is one of the most widely spread indigenous languages of southern South America. It is spoken by 6 million people in Paraguay (where it is...
  • Sardana Ivanova
    Apertium translation pair for Kazakh and Sakha
    I would like to develop Apertium translation pair for Kazakh and Sakha languages. It would benefit society in whole by keeping diversity supporting...
  • Evgenii Glazunov
    Bilingual dictionary enrichment via graph completion
    Graph representation is very promising because it represents a philosophical model of a metalanguage knowledge. Knowing several languages, I know...
  • Abinash Senapati
    Extend lttoolbox to have the power of HFST
    The aim of this project is to implement the support for morphographemics and weights in the lttoolbox transducer. The proposal focuses on extending...
  • Claude Balaguer
    Fra-oci/oci-fra translator
    I intend to work on a French-Occitan translation pair in order to provide a new translator, which will be useful first to the Occitan community but...
  • Anna Kondratjeva
    Improving language pairs by mining MediaWiki Content Translation postedits
    The purpose of this proposal is to create a toolbox for automatic improvement of lexical component of a language pair. This toolbox might become a...
  • Vidyadheesha D N
    Kannada-Marathi language translation
    I am adding a new language pair (Kannda-Marathi) to Apertium.
  • Anna Zueva
    Tatar and Bashkir: developing a language pair
    The tat-bak language pair already exists in Apertium, but is now in the nursery state. The aim of my project is to develop this language pair, fill...
  • kmurphy4
    This project aims to extend the functionality of the UD Annotatrix tool. This tool allows researchers to annotate universal dependency trees right...
  • O─čuz
    Uyghur-Turkish MT
    An MT for the closely related Turkic languages, Uyghur of the Karluk branch and Turkish of the Oghuz branch.