Apertium

License: GNU General Public License (GPL)

Mailing List: apertium-stuff@lists.sourceforge.net

Apertium develops a free/open-source platform for machine translation and language technology. We try and focus our efforts on lesser-resourced and marginalised languages, but also work with larger languages. The platform, including data for a large number of language pairs, a translation engine and auxiliary tools is being developed around the world, both in universities and companies (e.g. Prompsit Language Engineering) and by a growing numbers independent free-software developers. There are currently 40 published language pairs within the project (including a number of "firsts" — for example Spanish—Occitan, Breton—French, Basque—Spanish, North Sámi--Norwegian Bokmål and Kazakh-Tatar among others), and many more in development.

Completed Tasks

• [0] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [0] Disambiguate 500 words of Russian text.
• [0] Hand annotate 500 words of text from Wikipedia
• [10] Disambiguate 500 words of Russian text.
• [11] Disambiguate 500 words of Russian text.
• [12] Disambiguate 500 words of Russian text.
• [13] Disambiguate 500 words of Russian text.
• [14] Disambiguate 500 words of Russian text.
• [15] Disambiguate 500 words of Russian text.
• [16] Disambiguate 500 words of Russian text.
• [17] Disambiguate 500 words of Russian text.
• [18] Disambiguate 500 words of Russian text.
• [19] Disambiguate 500 words of Russian text.
• [1] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [1] Disambiguate 500 words of Russian text.
• [20] Disambiguate 500 words of Russian text.
• [2] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [2] Disambiguate 500 words of Russian text.
• [3] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [3] Disambiguate 500 words of Russian text.
• [4] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [4] Disambiguate 500 words of Russian text.
• [5] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [5] Disambiguate 500 words of Russian text.
• [6] Disambiguate 500 words of Russian text.
• [7] Disambiguate 500 words of Russian text.
• [8] Disambiguate 500 words of Russian text.
• [90] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [92] Convert 500 words of Finnish text in colloquial Finnish to literary Finnish
• [9] Disambiguate 500 words of Russian text.
• Abstract the formatting for the Html-tools interface.
• add city name support phenny/begiak timezone plugin
• Add other functions to begiak's git plugin
• Add permalink capability for generation and analysis to Html-tools
• Add phenny/begiak queue functions: replace, move, and random
• Add support for reordering to a bison syntax tree AST
• add support for timezone conversion to phenny/begiak
• An entry test for Apertium
• Apertium in 5 slides
• Apertium on Windows (installer)
• bilingual apertium-init bootstrap should handle --no-prob1 --no-pgen2 --no-rlx1 options
• Bison error token in transfer4
• Convert one part-of-speech from SALDO to Apertium .dix format
• Convert one part-of-speech from SALDO to Apertium .dix format
• Create a convertor for events for a MaxEnt POS tagger
• Create a python script to merge feature weights extracted from yasmet into a single file
• Detect target language
• Dictionary conversion
• Dictionary conversion in python
• Dictionary conversion in python
• Disambiguate 500 words of Gernan text.
• Disambiguate 500 words of Gernan text.
• Disambiguate 500 words of Gernan text.
• Disambiguate 500 words of text in German
• Disambiguate 500 words of text in German
• Document materials for a language not yet on our wiki
• Document phenny/begiak git plugin
• document the correspondences between the tagset used in the RNC tagged corpus and the Apertium tagset for Russian
• Drag-n-drop file translation on Html-tools
• figure out how to make folding work in the lexc plugin for vim
• Figure out why begiak's url catcher still has some encoding issues and fix
• Find translation bugs by using LanguageTool, and correct them
• Find translation bugs by using LanguageTool, and correct them
• fix begiak queues deletion
• fix how begiak's ethnologue plugin determines number of speakers
• fix phenny/begiak seen function
• fix scraper drivers and documentation
• georeference areas Russian is spoken
• georeference language areas for Central Asian languages: Kazakh
• geriaoueg hover functionality
• geriaoueg hover functionality
• geriaoueg language/pair selection
• geriaoueg language/pair selection
• geriaoueg lookup code
• Get bible aligner working (or rewrite it)
• greeting function for phenny/begiak
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Hand annotate 250 words of running text.
• Html-tools expanding textareas
• Implement a feature extractor for a MaxEnt POS tagger
• implement a pester plugin for begiak
• Import adjectives from azmorph into apertium-aze
• Import adverbs from azmorph into apertium-aze
• Import verbs from azmorph into apertium-aze
• improve phenny/begiak timezone data
• Improve the quality of a language pair of choice by adding 50 words to its vocabulary
• Improve the quality of a language pair of choice by adding 50 words to its vocabulary
• Improve the quality of a language pair of choice by adding 50 words to its vocabulary
• Installing Apertium in lightweight GNU/Linux distributions
• Investigate how orthographic modes on kk.wikipedia.org are implemented
• libvoikko support for OS X
• Light Apertium bootable ISO for small machines
• Localisation of tag attributes on Html-tools
• Make a new definition for our xml corpus format
• Make Apertium's scraper framework write the tree to disk every n seconds instead of every article
• Make apertium-viewer.html using APY
• make begiak's .queue display function work
• make scraper Writer fail gracefully on break and write output
• Make the script that generates "dixtables"on the wiki also create all the missing stats pages
• Manually spell-check running text in an apertium language of your choice
• Manually spell-check running text in an apertium language of your choice
• phenny/begiak apertium wiki module search capability
• phenny/begiak awikstats to count rlx sizes
• phenny/begiak awikstats to count t*x sizes
• phenny/begiak awikstats to report the revision of each monolingual file
• phenny/begiak blacklist for url interceptor
• phenny/begiak queue rename and reassign functions
• phenny/begiak relevant wiki module handle urls for wikis
• phenny/begiak tell/ask queue split long messages
• phenny/begiak tell/ask queue support deleting items from queue
• phenny/begiak tell/ask queue to support nick aliases
• Prototype unigram tagger.
• scraper for all wiktionary pages in a category
• Scraper for free forum content
• Scraper for free forum content
• Scraper for free forum content
• script to bootstrap an apertium bilingual module
• script to bootstrap an apertium module in hfst
• script to bootstrap an apertium module in lttoolbox
• SSL/HTTPS for Apertium.org
• Syntax tree visualisation using GNU bison
• Visualisation of bilingual dictionary development for language family visualisation tool
• Visualisation of monolingual dictionary development for language family visualisation tool
• Website translation in Html-tools
• What's difficult about this language pair?
• Write a contrastive grammar
• Write a contrastive grammar
• Write a contrastive grammar
• Write a general Apertium Stream Format parser in Python.
• write a mailing list reporter for phenny/begiak
• Write a program to extract Bulgarian inflections
• Write a program to extract Faroese adjective inflections
• Write a program to extract Faroese noun inflections
• Write a program to extract Faroese verb inflections
• Write a program to extract Greek adjective inflections
• Write a script to explain an Apertium machine translation in terms of its parts
• write a spider to change all ab(c)-xy(z)-stems references to ab(c)-xy(z)_stems
• Write code to generate an AST representing the bison parse tree