Apertium
Mailing List: https://lists.sourceforge.net/lists/listinfo/apertium-stuff
Apertium is a free/open-source machine translation platform, initially aimed at related-language pairs but recently expanded to deal with more divergent language pairs (such as English-Catalan). The platform provides: a language-independent 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. Apertium uses a shallow-transfer machine translation engine which processes the input text in stages, as in an assembly line: de-formatting, morphological analysis, part-of-speech disambiguation, shallow structural transfer, lexical transfer, morphological generation, and re-formatting. There are currently 33 published language pairs within the project (including a number of "firsts" — for example Spanish—Occitan, Breton—French, and Basque—Spanish among others), and several more in development.
Completed Tasks
- a d3 graph to display apertium language pairs
- Add 'translate-as-you-type' to the simple-html interface
- Add 100 noun stems to Apertium-lat - FIRST DECLENSION
- Add 100 nouns of 1st declension to apertium-latin
- Add 100 nouns of the 2nd declension ending in -er,ro to Apertium-Lat
- add argparse support to corpus xml2txt.py script
- Add language detection to the Apertium translation box
- Add language detection to the simple-html interface
- Add language identification to apertium-tolk
- Add missing chemical elements to the bidirectional dictionary en-ca
- Add missing chemical elements to the bidirectional dictionary es-ca
- Add support for direction restrictions to paradigm chopper
- Add the second declension in -STER/-STRI ex. magister,stri to apertium-lat
- Add the second declension in -US ex. amicus, i
- Add transitivity information to Armenian side of verb entries in bidix
- Albanian dictionary expansion
- Albanian dictionary expansion
- begiak error handling: catch errors in irc.py
- begiak github plugin
- begiak svn module fix: paths with common subpaths
- begiak svn module fix: repos should be listed in config file, not plugin
- begiak svn/git module features: deleted files and more detail
- begiak wikipedia and wiktionary modules: other language wikipedias
- bible scraper
- bible scraper improvements
- bible website scraper
- Catalogue Resources for Afshar
- Catalogue resources for Azerbaijani
- Catalogue Resources for Qashqai
- Catalogue resources: Amazigh
- Catalogue resources: Farsi
- Catalogue resources: Uzbek
- Catalogue ressources for Dutch
- Categorise albanian nouns by inflectional paradigm
- Check and fix the categorisation of 200 Albanian nouns (1)
- Check installation instructions for openSUSE
- Check installation instructions for Ubuntu
- Check installation instructions for Windows
- Check new language with HFST HOWTO
- Check new language with lttoolbox HOWTO
- Combobox improvements for apertium-tolk
- commit bot features and fixes: AI
- commit bot features and fixes: daemon/timing
- Correctly enter remaining Armenian nouns
- Create a corpus - Latin - Julius Caesar
- Create a corpus of Armenian from RFE/RL
- Create graphs of available pairs with graphviz for stable, Romance language and North Germanic language pairs
- Create tagged corpus of Armenian from EANC
- Design a nice javascript drop-down box
- Design a translation interface for Apertium in HTML/CSS
- document all new begiak features
- eleda plugin for begiak
- Expand Macedonian--Albanian transfer lexicon by 250 entries (1)
- Expand Macedonian--Albanian transfer lexicon by 250 entries (2)
- Extract a list of Russian adjectives with inflection from Russian Wiktionary
- Extract a list of Russian nouns with inflection from Russian Wiktionary
- Extract a list of Russian verbs with inflection from Russian Wiktionary
- Extract and sentence-align parallel text from Aravot.am
- Extract Armenian adjective inflection from Wiktionary
- Extract Armenian adjective translations from Wiktionary
- Extract Armenian adverb translations from Wiktionary
- Extract Armenian closed-category translations from Wiktionary
- Extract Armenian example sentences for nouns from Wiktionary
- Extract Armenian nominal declension for adjectives
- Extract Armenian noun inflection from Wiktionary
- Extract Armenian noun translations from Wiktionary
- Extract Armenian proper noun inflection from Wiktionary
- Extract Armenian proper noun translations from Wiktionary
- Extract Armenian verb inflection from Wiktionary
- Extract Armenian verb translations from Wiktionary
- Extract comparative forms for Russian adjectives from Wiktionary
- Extract remaining Armenian adjective translations from Wiktionary
- Extract remaining noun translations, and check for animacy in transfer lexicon
- figure out what's causing the newline issues in the RFE/RL scraper
- find a way to make apertium wiki use "databases"
- Find missing chemical elements in English-Catalan pair
- Find missing chemical elements in Spanish-Catalan pair
- Find out gender for Albanian nouns
- Find translations for a list of Armenian words
- Fix 200 testvoc errors in Armenian nouns
- fix begiak etymology and definition support
- fix begiak help messages for functions with digits
- Fix remaining Armenian adjective translations
- Fixing proper noun tags for macedonian
- Fixing proper noun tags for macedonian pt. 10
- FIXING PROPER NOUN TAGS FOR MACEDONIAN pt. 2
- FIXING PROPER NOUN TAGS FOR MACEDONIAN PT. 3
- Fixing proper noun tags for macedonian pt. 4
- Fixing proper noun tags for macedonian pt. 5
- Fixing proper noun tags for macedonian pt. 6
- Fixing proper noun tags for macedonian pt. 8
- Fixing proper noun tags for macedonian pt. 9
- Improve the language identification facility in the simplified HTML page for Apertium
- Improve the simplified HTML page for Apertium for visualization in mobile phones
- Improved testvoc script
- Interface the Apertium interface with the webservice API in Javascript
- Investigate and train sentence segmentation tools
- Investigate commit bot replacements
- Investigate how to extract parallel text from Armenian-Russian-English website
- Localisation of languages and to/from dropdowns in apertium-tolk
- Make a translation of the macedonian-english dictionary to bulgarian 1/5
- Make a translation of the macedonian-english dictionary to bulgarian 2/5
- Make a translation of the macedonian-english dictionary to bulgarian 3/5
- Make a translation of the macedonian-english dictionary to bulgarian 4/5
- Make a translation of the macedonian-english dictionary to bulgarian 5/5
- MAKE A TRANSLATION OF THE MACEDONIAN-ENGLISH DICTIONARY TO BULGARIAN 6/5
- Make apertium-tolk optionally dependent on apertium-dbus
- Manually create speling files for Armenian nouns on Wiktionary with 13 forms.
- Manually create speling files for Armenian nouns on Wiktionary with 14 forms.
- Manually create speling files for Armenian nouns on Wiktionary with 15 forms.
- Manually create speling files for Armenian nouns on Wiktionary with 27 forms.
- Names of bible books: Chuvash-Kalmyk pair
- Names of bible books: Kazakh-Tatar pair
- Names of bible books: remaining languages
- Paradigm name from frequency list in paradigm-chopper
- Port apertium-dbus to python3
- Port apertium-tolk to python3
- Port paradigm chopper to Python3 and ElementTree
- Port paradigm-review to Python3 and output pardefs by frequency
- Port speling-paradigms to python3
- Proofread the English to Irish translation of the 'Where is James' story in apertium-en-ga
- scrape Mongolian news article urls
- scrape Mongolian noun paradigms into yaml file
- scraper for free Chuvash news source
- scraper plugin for a free Mongolian news source
- scraper plugin for a free Mongolian news source
- scraper plugin for a free Mongolian news source
- scraper plugin for free Chuvash news source
- script to count stems in bidix over svn
- script to generate list of apertium pairs
- script to scrape Mongolian news article urls
- Set up commit bot on Apertium server
- Translate macedonian verbs to bulgarian (1 / 6)
- Translate macedonian verbs to bulgarian (2 / 6)
- Translate macedonian verbs to bulgarian (3 / 6)
- Translate macedonian verbs to bulgarian (4 / 6)
- Translate macedonian verbs to bulgarian (5 / 6)
- Translate macedonian verbs to bulgarian (6 / 6)
- Translate the macedonian-english dictionary to bulgarian
- Translating macedonian adjectives to bulgarian pt. 1
- Update apertium-dbus to use the -z option of tools that support it
- uyghur quran scraper and more bible book titles
- write a 5-element comparative grammar for apertium-fa-en (Farsi-English)