Ideas for Google Summer of Code

From Apertium
Jump to: navigation, search

Contents

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, add your name to "Interested mentors" using ~~~

The page is intended as an overview of the kind of projects we have in mind. If one of them particularly piques your interest, please come and discuss with us on #apertium on irc.freenode.net, mail the mailing list, or draw attention to yourself in some other way.

Note that, if you have an idea that isn't mentioned here, we would be very interested to hear about it.

Here are some more things you could look at:


[edit] List

[edit] Bring a released language pair up to state-of-the-art quality

  • Difficulty:
    2. Medium
  • Required skills:
    XML, a scripting language (Python, Perl), good knowledge of the language pair adopted.
  • Description:
    Take a released language pair, and drastically improve the performance both in terms of coverage, and in terms of translation quality. This will involve working with dictionaries, transfer rules, scripting, corpora. The objective is to make an Apertium language pair state-of-the-art, or close to state-of-the-art in terms of translation quality. This will involve improving coverage to 95-98% on a range of corpora and decreasing word error rate by 30-50%. For example if the current word error rate is 30%, then it should be reduced to 15-20%.
  • Rationale:
    Apertium has quite a broad coverage of language pairs, but few of these pairs offer state-of-the-art translation quality. We think broad is important, but deep coverage is important too.
  • Mentors:
    Francis Tyers, Mikel Forcada
  • read more...

[edit] Adopt an unreleased language pair

  • Difficulty:
    3. Entry level
  • Required skills:
    XML, a scripting language (Python, Perl), good knowledge of the language pair adopted.
  • Description:
    Take on an orphaned unreleased language pair, and bring it up to release quality results. What this quality will be will depend on the language pair adopted, and will need to be discussed with the prospective mentor. This will involve writing linguistic data (including morphological rules and transfer rules — which are specified in a declarative language — and possibly Constraint Grammar rules if that is relevant)
  • Rationale:
    Apertium has a few pairs of languages (e.g. mt-he, ga-gd, ur-hi, pl-cs, sh-ru, etc...) that are orphaned, they don't have active maintainers. A lot of these pairs have a lot of work already put in, just need another few months to get them to release quality. See also Incubator
  • Mentors:
    Francis Tyers, Jimregan, Kevin Scannell, Trondtr, Unhammer, Darthxaher, Firespeaker, Hectoralos, Hrvoje Peradin, Jacob Nordfalk, Mikel Forcada, Vinit Ravishankar, Aida Sundetova
  • read more...

[edit] Extend lttoolbox to have the power of HFST

  • Difficulty:
    1. Hard
  • Required skills:
    C++, XSLT, XML
  • Description:
    Extend lttoolbox (perhaps writing a preprocessor for it) so that it can be used to do the morphological transformations currently done with HFST. And yes, of course, writing something that translates the current HFST format to the new lttolbox format. Proof of concept: Come up with a new format that can express all of the features found in the Kazakh transducer; implement this format in Apertium; Implement the Kazakh transducer in this format and integrate it in the English--Kazakh pair.
  • Rationale:
    Some language pairs in Apertium use HFST where most language pairs use Apertium's own lttoolbox. This is due to the fact that writing morphologies for languages that have features such as the vowel harmony found in Turkic languages is very hard with the current format supported by lttoolbox. The mixture of HFST and lttoolbox makes it harder for people to develop some language pairs.
  • Mentors:
    Mikel Forcada, Tommi A Pirinen, User:Unhammer, Mikel Forcada, mentors wanted
  • read more


[edit] Discontiguous multiwords

  • Difficulty:
    2. Medium
  • Required skills:
    C++, Knowledge of FSTs
  • Description:
    The task will be to develop, or adapt a module to deal with these kind of contiguous multiword expressions, for example, taking 'liggja ekki fyrir' and reordering it as 'liggja# fyrir ekki'.
  • Rationale:
    In many languages, such as English, Norwegian and Icelandic, there are discontiguous multiwords, e.g. phrasal verbs, that we cannot easily support. For example 'liggja ekki fyrir' in Icelandic should be translated in English as 'to be not clear', but we cannot have 'liggja fyrir' as a traditional multiword because of the extra 'adverb', or it could even be a whole NP.
  • Mentors:
    Francis Tyers
  • read more...

[edit] lint for Apertium

  • Difficulty:
    3. Entry level
  • Required skills:
    Python, C++, XML, autotools
  • Description:
    Make a program which tests Apertium data files for suspicious or unrecommended constructs (likely to be bugs).
  • Rationale:
    Somtimes when several people are working on the same code, things can get repeated, or beginners can make unrecommended changes. A lint tester would help people write standard code for dictionaries and transfer files.
  • Mentors:
    Mikel Forcada, Vinit Ravishankar (co-mentors wanted)
  • read more...

[edit] Robust recursive transfer

  • Difficulty:
    1. Hard
  • Required skills:
    Python, XML, linguistics
  • Description:
    The purpose of this task would be to create a module to replace the apertium-transfer module(s) which will parse and allow transfer operations on an input.
  • Rationale:
    Currently we have a problem with very distantly related languages that have long-distance constituent reordering, because we can only do finite-state chunking.
  • Mentors:
    Francis Tyers, Sortiz, Mikel Forcada, Juan Antonio Pérez
  • read more...

[edit] Weighted transfer rules

  • Difficulty:
    1. Hard
  • Required skills:
    Python, C++, linguistics
  • Description:
    The purpose of this task is to add weights to our transfer rules and allow conflicting rule patterns to be handled by combining (lexicalised) weights.
  • Rationale:
    Currently our transfer rules are applied longest-match left-to-right (LRLM). When two rule patterns conflict the first one is chosen.
  • Mentors:
    Francis Tyers, Tommi Pirinen, Mikel Forcada
  • read more...


[edit] Overhaul Java frontends to use native and web backends

  • Difficulty:
    1. Hard
  • Required skills:
    Java, C++, Android
  • Description:
    Overhaul the OmegaT and other lttoolbox-java based frontends to instead be able to download and instrument the native toolchain, as well as use online APY-based services
  • Rationale:
    We have a Java library, lttoolbox-java, which runs entirely on the JVM and Android Dalvik, and this is fine. The main drawback at the moment is that it doesn't support HFST and also doesn't support CG, which a number of language pairs rely on (for example Sámi, Turkic, Breton, Welsh etc). The other drawback is that nobody is keeping the Java port up to date, so it tends to lag behind features and fixes that the native tools get. The objective of this task is to instead use the native backends where possible, and also use web-based backends where needed.
  • Mentors:
    Tino Didriksen, Tommi Pirinen
  • ...

[edit] Automatic blank handling

  • Difficulty:
    2. Medium
  • Required skills:
    C++, XML
  • Description:
    Let the C++ modules deal with formatting, treating some tags as word-bound.
  • Rationale:
    Our current format handling is brittle, requiring transfer rules to explicitly deal with blanks, and some times inevitably outputting them in the wrong order. This project is to do blank-handling automatically, by treating some blanks as "glued to words" (e.g. italics, emphasis), and others as paragraph-level blanks.
  • Mentors:
    Unhammer, Tino Didriksen, Mikel Forcada
  • read more #1, read more #2

[edit] Integration and debugging tools for Grammatical Framework

  • Difficulty:
    2. Medium
  • Required skills:
    Haskell, C, XML
  • Description:
    The objective of this task is to create a suite of tools for Grammatical Framework (GF) to facilitate interoperability with Apertium and other tools.
  • Rationale:
    Grammatical Framework has a ton of resources, but people familiar with Apertium may find the way of using them a bit alien. The idea of this task is to make some tools for GF to make it more easily pick-uppable for Apertium developers and users.
  • Mentors:
    Francis Tyers
  • read more...


[edit] Improvements to the Apertium website

  • Difficulty:
    3. Entry level
  • Required skills:
    Python, HTML, JS
  • Description:
    Our web site is pretty cool already, but it's missing things like dictionary/synonym lookup, support for several variants of one language, reliability visualisation, (reliable) webpage translation, feedback, etc.
  • Rationale:
    https://apertium.org is what most people know us by, it should show off more of the things we are capable of :-)
  • Mentors:
    Jonathan
  • read more...

[edit] Develop a spell checking system

  • Difficulty:
    2. Medium
  • Required skills:
    Python, HTML, JS, autotools
  • Description:
    Make it easier to make spell checkers from all our transducers, and integrate them into the web site. Our transducers can easily be used as spellcheckers by compiling them using HFST. Many languages based on HFST in the languages module of our repository have this set up, but not all of them.
  • Rationale:
    Spell checking is one of more useful services our language resources can provide. Being able to easily provide spell checking is important both for language communities to be able to use our resources and as a new entry point for prospective developers. This projects involves creating interfaces to spell checking both for our web site, and for developers.
  • Mentors:
    Jonathan
  • read more...

[edit] Offline, desktop GUI for Apertium

  • Difficulty:
    3. Entry level
  • Required skills:
    GTK or Qt; Python/Ruby/C++/?
  • Description:
    Create a user-friendly desktop GUI for Apertium that "just works".
  • Rationale:
    We currently have no working and maintained offline GUI for Apertium for use on desktops. The goal of this task is to make a nice GUI that works with the offline packages, to replace the aging apertium-tolk. It should use apy, work with offline packages, and offer at least the features of apertium-html-tools.
  • Mentors:
    Unhammer, Tino Didriksen (C++ & Qt5)
  • read more...

[edit] User-friendly lexical selection training

  • Difficulty:
    2. Medium
  • Required skills:
    Python, C++, shell scripting
  • Description:
    Make it so that training/inference of lexical selection rules is a more user-friendly process
  • Rationale:
    Our lexical selection module allows for inferring rules from corpora and word alignments, but the procedure is currently a bit messy, with various scripts involved that require lots of manual tweaking, and many third party tools to be installed. The goal of this task is to make the procedure as user-friendly as possible, so that ideally only a simple config file would be needed, and a driver script would take care of the rest.
  • Mentors:
    Unhammer, Francis Tyers, Mikel Forcada
  • read more...

[edit] Light alternative format for all XML files in an Apertium language pair

  • Difficulty:
    1. Hard
  • Required skills:
    Python, C++, shell scripting, XSLT, flex
  • Description:
    Make it possible to edit and develop language data using a format that is lighter than XML
  • Rationale:
    In most Apertium language pairs, monolingual dictionaries, bilingual dictionaries, post-generation rule files and structural transfer rule files are all written in XML. While XML is easy to process due to explicit tagging of every element, it is tedious to deal with, particularly when it comes to structural transfer rules. Apertium's precursor, interNOSTRUM, had lighter text based formats. The task involves: (a) designing and documenting an interNOSTRUM-style format for all of the XML language data files in a language pair; (b) writing converters to XML and from XML that are fully roundtrip-compliant: (c) designing a way to synchronize changes when both the XML and the non-XML format are used simultaneously in a specific language pair.
  • Mentors:
    Mikel Forcada, Juan Antonio Pérez, pair.
  • read more...

[edit] Eliminate dictionary trimming

  • Difficulty:
    0. Very Hard
  • Required skills:
    C++, Finite-State Transducers
  • Description:
    Eliminate the need for trimming the monolingual dictionaries, in order to preserve and take advantage of maximal source language analysis.
  • Rationale:
    Why we trim mentions several technical reasons for why trimming away monolingual information is currently needed. Unfortunately, this limitation means that a lot of useful contextual information is lost. It would be ideal if the source language could be fully analyzed independent of target language, with any untranslated part fed back into the source language generator.
  • Mentors:
    ? (Tommi Pirinen a.k.a. Flammie interested, but low on time if alone)
  • Work around everything in Why we trim

[edit] Constraint-grammar aware unsupervised training of the part-of-speech tagger

  • Difficulty:
    2. Medium
  • Required skills:
    shell scripting, python, etc.
  • Description:
    Obtain better source-language part-of-speech taggers when no tagged corpus is available to train them
  • Rationale:
    When a statistical tagger is used with Apertium, it is possible to train it in an unsupervised manner (that is, without a tagged corpus) using the Baum-Welch algorithm. When Constraint Grammar rules are used, many analyses are removed for ambiguous words. A usual combination is to use statistical part-of-speech tagging after constraint grammar ambiguity reduction. However, the current method to unsupervisedly train the past-of-speech tagger trains it regardless of the reduction in ambiguity that the constraint grammar rules bring about. The task is to make it easy for a language-pair developer to retrain the part-of-speech tagger on an untagged corpus at any time, taking into account the CG rules. It should work with both taggers, the one using Hidden Markov Models and the one using sliding windows.
  • Mentors:
    Mikel Forcada, Felipe Sánchez-Martínez
  • Contact User:Mlforcada for more information.

[edit] Bilingual dictionary enrichment via graph completion

  • Difficulty:
    0. Very hard
  • Required skills:
    shell scripting, python, XSLT, XML
  • Description:
    Generate new entries for existing or new bilingual dictionaries using graphic representations of bilingual correspondences as found in all existing dictionaries (note that this idea defines a rather open-ended task to be discussed in detail with mentors).
  • Rationale:
    Apertium bilingual dictionaries establish correspondences between lexical forms in a number of language pairs. Connections among them may be used to infer new entries for existing or new language pairs using graphs. The graphs may be directly generated from Apertium bidixes and exploiting using ideas that had already been proposed in Apertium or using existing RDF representations of parts of their content, which may benefit from the information coming from being linked to other resources.
  • Mentors:
    Mikel Forcada, Francis Tyers, Jorge Gracia
  • read more... read even more...
Personal tools