A free/open-source machine translation platform

Apertium is a shallow-transfer machine translation system, which uses finite state transducers for all of its lexical transformations, and hidden Markov models and/or constraint grammars for part-of-speech tagging or word category disambiguation.

Existing machine translation systems available at present are mostly commercial, use proprietary technologies, which makes them very hard to adapt to new usages; furthermore, they use different technologies across language pairs, which makes it very difficult, for instance, to integrate them in a single multilingual content management system. Finally, most of them are not available for most of the languages in the world, as they rely heavily on resources that are not available for them.

Apertium uses a language-independent specification, to allow for the ease of contributing to Apertium, more efficient development, and enhancing the project's overall growth.

At present, Apertium has released more than 40 stable language pairs, delivering fast translation with reasonably intelligible results. Being an open-source project, Apertium provides tools for potential developers to build their own language pair and contribute to the project.

lightbulb_outline View ideas list

Technologies

  • c++
  • python
  • xml
  • bash

Topics

  • Other
  • machine translation
  • natural language processing
  • less-resourced languages
comment IRC Channel
email Mailing list
mail_outline Contact email

Apertium 2019 Projects

  • Tanmai Khanna
    Anaphora Resolution
    Anaphora resolution is the problem of resolving references to earlier items in the discourse. This most commonly appears as pronoun resolution where...
  • Sharapat Kalabaev
    Develop a releasable Uzbek-Qaraqalpaq translation pair
    In this project I am going to create a new translation pair between Uzbek and Qaraqalpaq. There is no other single translator between these two...
  • Eden-Grace Muamba
    English-Lingala language pair
    An ‘English-Lingala’ language pair using Apertium rule-based machine translation system.
  • Aboelhamd Aly
    Improve/Extend weighted transfer rules module
    Ambiguous patterns are ones that more than one transfer rule could be applied to. Apertium resolves this ambiguity by applying the left-to-right...
  • Alyaxey Yaskevich
    Improvement of Annotatrix project
    Bug fixes and feature implementations for Annotatrix tool
  • Hèctor Alòs Font
    Improving the Catalan-Italian and Catalan-Portuguese language pairs
    In this project there are two major goals: 1) improving the existing translators from Italian to Catalan, from Portuguese to Catalan and from Catalan...
  • vaydheesh
    Python API/library for Apertium
    Apertium is a free/open-source rule-based machine translation platform implemented in C++. Right now, the project is calling Apertium binaries as...
  • Daniel Swanson
    Recursive Transfer
    Build a GLR parser-generator as an alternative to the current chunking system to better support long-distance phrasal reordering.
  • Oğuz
    Turkic MT improvements
    Refining four Turkic MTs: uig-tur, kyr-tur, uzb-tur and tat-tur
  • Amr Keleg
    Unsupervised weighting of automata
    Finite state automata/ transducers are currently used in lots of application including machine translation. One of the most challenging parts of...
close

2019