Difference between revisions of "Ideas for Google Summer of Code"
Jump to navigation
Jump to search
Line 14: | Line 14: | ||
| '''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 || [[User:Francis Tyers|Francis Tyers]] |
| '''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 || [[User:Francis Tyers|Francis Tyers]] |
||
|- |
|- |
||
| '''Lexical selection''' || High || Write a prototype lexical selection module for Apertium using a combination of rule-based and statistical approaches. || Lexical selection is the task of choosing a sense (meaning) for a word out of a number of possible senses (related to [[word sense disambiguation]]), when languages are close, they often share semantic ambiguity, when they are further apart they do not, so for example Spanish "estación" can be either "station", "season" or "resort" in English. Lexical selection is the task of choosing the right one. || C++, XML, good knowledge of statistics. || |
| '''Lexical selection''' || Very High || Write a prototype lexical selection module for Apertium using a combination of rule-based and statistical approaches. || Lexical selection is the task of choosing a sense (meaning) for a word out of a number of possible senses (related to [[word sense disambiguation]]), when languages are close, they often share semantic ambiguity, when they are further apart they do not, so for example Spanish "estación" can be either "station", "season" or "resort" in English. Lexical selection is the task of choosing the right one. || C++, XML, good knowledge of statistics. || |
||
|- |
|- |
||
| '''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. || [[User:Francis Tyers|Francis Tyers]] |
| '''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. || [[User:Francis Tyers|Francis Tyers]] |
||
Line 22: | Line 22: | ||
| '''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. || [[User:Francis Tyers|Francis Tyers]] |
| '''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. || [[User:Francis Tyers|Francis Tyers]] |
||
|- |
|- |
||
| '''Three-level'''<br/>'''transfer training''' || High || Re-working apertium-transfer-training-tools to generate rules for three-level transfer (chunk, interchunk, postchunk), currently it only generates single-level rules. This would also involve porting it to use Unicode || Apertium-transfer-training-tools is a cool piece of software that generates shallow-transfer rules from aligned parallel corpora. It could greatly speed up the creation of new language pairs by generating rules that would otherwise have to be written by human linguists. || C++, knowledge of Giza++, Perl considered a plus. || |
| '''Three-level'''<br/>'''transfer training''' || Very High || Re-working apertium-transfer-training-tools to generate rules for three-level transfer (chunk, interchunk, postchunk), currently it only generates single-level rules. This would also involve porting it to use Unicode || Apertium-transfer-training-tools is a cool piece of software that generates shallow-transfer rules from aligned parallel corpora. It could greatly speed up the creation of new language pairs by generating rules that would otherwise have to be written by human linguists. || C++, knowledge of Giza++, Perl considered a plus. || |
||
|- |
|- |
||
| '''Automated lexical'''<br/>'''extraction''' || High || Writing a C++ wrapper around Markus Forsberg's [http://www.cs.chalmers.se/~markus/extract/ Extract] tool (version 2.0) as a library to allow it to be used with Apertium paradigms and TSX files as input into its paradigms and constraints. || One of the things that takes a lot of time when creating a new language pair is constructing the [[monodix|monodices]]. The extract tool can greatly reduce the time this takes by matching lemmas to paradigms based on distribution in a corpus. || Haskell, C++, XML || [[User:Francis Tyers|Francis Tyers]] |
| '''Automated lexical'''<br/>'''extraction''' || High || Writing a C++ wrapper around Markus Forsberg's [http://www.cs.chalmers.se/~markus/extract/ Extract] tool (version 2.0) as a library to allow it to be used with Apertium paradigms and TSX files as input into its paradigms and constraints. || One of the things that takes a lot of time when creating a new language pair is constructing the [[monodix|monodices]]. The extract tool can greatly reduce the time this takes by matching lemmas to paradigms based on distribution in a corpus. || Haskell, C++, XML || [[User:Francis Tyers|Francis Tyers]] |
||
|- |
|- |
||
| '''Generating grammar'''<br/>'''checkers''' || Medium || The data that come with Apertium (morphological analysers) could be used to create grammar checkers. This task would be to work on an automatic converter for Apertium formats to other popular grammar checker formats, or alternatively work on a standalone grammar checker. Maybe using something like [http://www.languagetool.org/ languagetool]. || Grammar checkers can be useful, for languages other than English moreso. They are one of the "must have" items of language technology. If we can re-use Apertium data for this purpose it will help both the project (by making creating new language pairs more rewarding) and the language communities (by making more useful software). || XML, whatever programming language and natural language are used for testing. || [[User:Francis Tyers|Francis Tyers]] |
| '''Generating grammar'''<br/>'''checkers''' || Medium || The data that come with Apertium (morphological analysers) could be used to create grammar checkers. This task would be to work on an automatic converter for Apertium formats to other popular grammar checker formats, or alternatively work on a standalone grammar checker. Maybe using something like [http://www.languagetool.org/ languagetool]. || Grammar checkers can be useful, for languages other than English moreso. They are one of the "must have" items of language technology. If we can re-use Apertium data for this purpose it will help both the project (by making creating new language pairs more rewarding) and the language communities (by making more useful software). || XML, whatever programming language and natural language are used for testing. || [[User:Francis Tyers|Francis Tyers]] |
||
|- |
|||
|} |
|} |
||
Revision as of 11:47, 4 March 2008
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 ~~~
Maybe take a look at some open bugs ?
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)[1] tools for morphological analysis/generation could be used in place of lttoolbox, and the constraint grammars from VISL[2] 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 | Very High | Write a prototype lexical selection module for Apertium using a combination of rule-based and statistical approaches. | Lexical selection is the task of choosing a sense (meaning) for a word out of a number of possible senses (related to word sense disambiguation), when languages are close, they often share semantic ambiguity, when they are further apart they do not, so for example Spanish "estación" can be either "station", "season" or "resort" in English. Lexical selection is the task of choosing the right one. | C++, XML, good knowledge of statistics. | |
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 |
Three-level transfer training |
Very High | Re-working apertium-transfer-training-tools to generate rules for three-level transfer (chunk, interchunk, postchunk), currently it only generates single-level rules. This would also involve porting it to use Unicode | Apertium-transfer-training-tools is a cool piece of software that generates shallow-transfer rules from aligned parallel corpora. It could greatly speed up the creation of new language pairs by generating rules that would otherwise have to be written by human linguists. | C++, knowledge of Giza++, Perl considered a plus. | |
Automated lexical extraction |
High | Writing a C++ wrapper around Markus Forsberg's Extract tool (version 2.0) as a library to allow it to be used with Apertium paradigms and TSX files as input into its paradigms and constraints. | One of the things that takes a lot of time when creating a new language pair is constructing the monodices. The extract tool can greatly reduce the time this takes by matching lemmas to paradigms based on distribution in a corpus. | Haskell, C++, XML | Francis Tyers |
Generating grammar checkers |
Medium | The data that come with Apertium (morphological analysers) could be used to create grammar checkers. This task would be to work on an automatic converter for Apertium formats to other popular grammar checker formats, or alternatively work on a standalone grammar checker. Maybe using something like languagetool. | Grammar checkers can be useful, for languages other than English moreso. They are one of the "must have" items of language technology. If we can re-use Apertium data for this purpose it will help both the project (by making creating new language pairs more rewarding) and the language communities (by making more useful software). | XML, whatever programming language and natural language are used for testing. | Francis Tyers |
Notes
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
- Wikipedia: Desambiguación léxica basada en ventana deslizante (in Spanish)
- Sanchez-Villamil, E., Forcada, M. L., and Carrasco, R. C. (2005). "Unsupervised training of a finite-state sliding-window part-of-speech tagger". Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence, vol. 3230, p. 454-463
- Automated lexical extraction
- M. Forsberg H. Hammarström A. Ranta. "Morphological Lexicon Extraction from Raw Text Data". FinTAL 2006, LNAI 4139, pp. 488--499.