Ideas for Google Summer of Code

From Apertium
Revision as of 22:21, 1 March 2008 by Francis Tyers (talk | contribs)
Jump to navigation Jump to search

This is the ideas page for Google Summer of Code, here you can find ideas on interesting projects that would make Apertium more useful for people and improve or expand our functionality. If you have an idea please add it below, if you think you could mentor someone in a particular area -- or just have interests or ideas for that, add your name to "Interested parties" using ~~~

Task Difficulty Description Rationale Requirements Interested
parties
Improve interoperability Medium Either to modify Apertium to accept different formats, to modify the other tools to accept the Apertium format, or alternatively write some kind of generic "glue" code that converts between them. There is a lot of great free software that could be used with the Apertium engine. For example the Stuttgart FST (SFST) tools for morphological analysis/generation could be used in place of lttoolbox, and the constraint grammars from VISL could be used in place of apertium-tagger. Unfortunately these, along with many other tools have incompatible input/output formats. C, C++, XML Francis Tyers
Accent and diacritic
restoration
Medium Create an optional module to restore diacritics and accents on incoming text. Many languages use diacritics and accents in normal writing, and Apertium is designed to use these, however in some places, especially for example. instant messaging, irc, searching in the web etc. these are often not used or untyped. This causes problems as for the engine, traduccion is not the same as traducción. C, C++, XML, familiarity with linguistic issues Francis Tyers
Handling texts without
accents or diacritics
Medium Modify the linguistic data in an Apertium language-pair package so that it can accept text without accents or diacritics (or partially diacriticized). No programming expected. Just dictionary modification and retraining. The task may constitute an alternative solution to the problem in the previous task. see: Accent and diacritic restoration Perl or Python, familiarity with linguistic issues. Mlforcada
Porting Medium Port Apertium to Windows and Mac OS/X complete with nice installers and all that jazz. Apertium currently compiles on Windows (see Apertium on Windows), but we'd like to see it compile with a free toolchain. While we all might use GNU/Linux, there are a lot of people out there who don't, some of them use Microsoft's Windows, others use Mac OS. It would be nice for these people to be able use Apertium too. C++, autotools, experience in programming on Windows or Mac Francis Tyers
Lexical selection High
Interfaces Low Create plugins or extensions for popular free software applications to include support for translation using Apertium. We'd expect at least OpenOffice and Firefox, but to start with something more easy we have half-finished plugins for Gaim and XChat that could use some love. The more the better! Apertium currently runs as a stand alone translator. It would be great if it was integrated in other free software applications. For example so instead of copy/pasting text out of your email, you could just click a button and have it translated in place. Depends on the application chosen, but probably C, C++, Python or Perl. Francis Tyers
Sliding window based
part-of-speech tagging
High Writing a complete drop-in replacement for the Apertium part-of-speech tagger based on the sliding-window part-of-speech tagger of Sánchez-Villamil et al. (2004) [1] and Sánchez-Villamil et al. (2005) [2] (Apertium currently uses hidden Markov models). The specification file should be as similar as possible as the one used now. The taggers described are very intuitive and may easily be turned into a compact set of finite-state rules (no need to handle probabilities after training), and may be trained in an unsupervised manner. Depending on the language, the sliding window of words to be analyzed may be configured to suit it. C or C++, basic knowledge of the grammar of the language(s) involved Mlforcada
Documentation Low Improving, updating and adding to the existing Apertium documentation. Particularly, a HOWTO for writing transfer rules. This will involve either selecting a current language pair with little-transfer, or creating a new language pair, and documenting how you approach writing rules. Apertium has (or so we've been told) pretty good documentation, but as everyone knows, documentation can always be improved. For example: at the moment we're lacking HOWTO style documentation for transfer rules. XML, good grammatical knowledge of the syntax of the language pair you're approaching. Francis Tyers

Further reading

Accent and diacritic restoration
  • Simard, Michel (1998). "Automatic Insertion of Accents in French Texts". Proceedings of EMNLP-3. Granada, Spain.
  • Rada F. Mihalcea. (2002). "Diacritics Restoration: Learning from Letters versus Learning from Words". Lecture Notes in Computer Science 2276/2002 pp. 96--113
  • "G. De Pauw, P. W. Wagacha; G.M. de Schryver (2007) "Automatic diacritic restoration for resource-scarce languages". Proceedings of Text, Speech and Dialogue, Tenth International Conference. pp. 170--179
Lexical selection
  • Ide, N. and Véronis, J. (1998) "Word Sense Disambiguation: The State of the Art". Computational Linguistics 24(1)
Sliding-window based part-of-speech tagging