-
Notifications
You must be signed in to change notification settings - Fork 4
LogonTop
The LOGON infrastructure (and source tree) is a collection of software, grammars, and other linguistic resources to facilitate experimentation with transfer-based machine translation (MT). To a large degree, the LOGON tree packages resources that exist independently, specifically the core of the open-source [http://www.delph-in.net DELPH-IN] tool chain and several of the DELPH-IN grammars. These include, among others, the [http://www.delph-in.net/lkb LKB], [http://www.delph-in.net/pet PET], and itsdb software systems, and the [http://www.delph-in.net/erg LinGO ERG], [http://www.delph-in.net/gg GG], [http://www.delph-in.net/jacy JaCY], and [http://www.delph-in.net/srg SRG] broad-coverage grammars for English, German, Japanese, and Spanish, respectively. Additionally, the tree includes pre-compiled versions of other packages, for example [http://chasen.aist-nara.ac.jp/chasen/distribution.html.en ChaSen] (for Japanese pre-processing), [http://garraf.epsevg.upc.es/freeling/ FreeLing] (Spanish pre-processing), [http://tadm.sourceforge.net/ TADM] (for MaxEnt experimentation), [http://www.coli.uni-saarland.de/~thorsten/tnt/ TnT] (for English PoS tagging), and [http://www.coli.uni-saarland.de/projects/chorus/utool/ UTool] (for MRS manipulation).
The LOGON tree was originally developed by the Norwegian [http://www.emmtee.net LOGON] and [http://www.emmtee.net/index.php?page=7 HandOn] research projects, working on translation from Norwegian to English. For Norwegian analysis, these projects employed (an extended version of) the [http://maximos.aksis.uib.no/Aksis-wiki/Oslo-Bergen_Tagger Oslo-Bergen Tagger] (OBT) and the [http://www.hf.uib.no/i/LiLi/SLF/Dyvik/norgram/ NorGram] LFG implementation. Both resources are released under open-source licenses as part of the LOGON tree. However, to actually run the Norwegian–English instantiation of the system (dubbed NoEn), the proprietary [http://www2.parc.com/isl/groups/nltt/xle/ XLE] LFG system is required, which cannot be part of the freely available LOGON distribution. Please see the LogonExtras page for instructions on how to install proprietary add-ons to the LOGON tree, e.g. for sites holding a valid XLE license. Furthermore, there is an [http://noen.emmtee.net on-line interface] to the Norwegian–English demonstrator.
In subsequent collaborations between the original LOGON developers and DELPH-IN researchers in Germany, Japan, and the USA, additional language pairs were added. As of late 2008, these include German–English and Japanese–English (and, albeit lesser developed, the inverse directions of translation), as well as a plethora of 'baby' MT systems built from a collection of smaller grammars based on the LinGO [http://www.delph-in.net/matrix Grammar Matrix]. In a sense, the LOGON tree functions similar to a Linux distribution: it combines a complex set of individual components, aiming to provide ease of installation and a certain degree of uniformity, inter-operability, and quality assurance. The system is available exclusively for Linux (on 32-bit or 64-bit x86 architectures). As of November 2008, all system development and distribution is through the [http://subversion.tigris.org/ SubVersion] (SVN) revision management system. Please see the LogonInstallation page for details. Regrettably, only a very limited amount of documentation is available, a property that the LOGON tree shares with a number of the core DELPH-IN resources.
Following is a list of topics for which documentation exists (or should be ported from LOGON-internal workspace postings). Feel free to add additional materials, but please make sure to create adequate wiki names for new pages, all prefixed with Logon.
-
LogonInstallation: System Requirements, Download and Installation Notes
-
LogonMrs: Background on the Specific Use of the MRS Formalism in LOGON
-
LogonProcessing: Documentation of Various Batch Processing Facilities
-
LogonModeling: Information on Training and Applying Various Statistical Models
-
LogonWishlist: Feature Requests Contributed by LOGON Co-Developers and Users
Further information on the LOGON software and consortium can be found at the [http://www.emmtee.net/ project web site]; the following publication provides an overview of most of the core pieces:
-
Stephan Oepen, Erik Velldal, Jan Tore Lønning, Paul Meurer, Victoria Rosén, and Dan Flickinger.
[http://share.emmtee.net/pub/bscw.cgi/d64459/tmi07.pdf Towards hybrid quality-oriented machine translation. On linguistics and probabilities in MT]. In Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation. Skövde, Sweden, 2007
-
Stephan Oepen, Helge Dyvik, Jan Tore Lønning, Erik Velldal, Dorothee Beermann, John Carroll, Dan Flickinger, Lars Hellan, Janne Bondi Johannessen, Paul Meurer, Torbjørn Nordgård, and Victoria Rosén.
[http://share.emmtee.net/pub/bscw.cgi/d23044/tmi04.pdf Som å kapp-ete med trollet? Towards MRS-based Norwegian-English Machine Translation]. In Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation, pp. 11–20. Baltimore, MD.
The first paper discussing the use of Minimal Recursion Semantics in machine translation is:
-
Ann Copestake, Dan Flickinger, Rob Malouf, Susanne Riehemann and Ivan Sag, 1995.
[http://www.cl.cam.ac.uk/~aac10/papers/tmi95.ps.gz Translation using Minimal Recursion Semantics] (ACQUILEX II WP NO. 61) In Proceedings of The Sixth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI95) pp. 15–32. Leuven, Belgium.
An example of the extension of the LOGON machinery to a new language pair can be seen in
-
Francis Bond, Stephan Oepen, Melanie Siegel, Ann Copestake, and Dan Flickinger (2005)
[http://www2.nict.go.jp/x/x161/en/member/bond/pubs/2005-summit-osmt.pdf Open source machine translation with DELPH-IN]. In Open-Source Machine Translation: Workshop at MT Summit X, pp 15–22. Phuket, Thailand.
For additional information, there is an archived [http://lists.emmtee.net/mailman/listinfo/logon mailing list] for the LOGON tree. For additional questions, please feel free to contact Stephan Oepen (oe at ifi.uio.no), the technical manager for the original LOGON consortium.
Home | Forum | Discussions | Events