Language Technology at UiT

The Divvun and Giellatekno teams build language technology aimed at minority and indigenous languages

View GiellaLT on GitHub divvungiellatekno/giellalt.uit.no

Meeting setup

Agenda

Cf. one of the following, depending on context:

Opening, agenda review, participants

Opened at 09:47.

Present: Børre, Ciprian, David, Jovsset, Maja Lisa, Sjur, Thomas, Tomi, Trond

Absent: none

Agenda accepted, with one addition under Other.

Updated task status since last meeting

Børre

Ciprian

David

Jovsset

Per-Eric

Maja

Saara

Sjur

Thomas

Tomi

Trond

Pedagogical software online

Added a place-name fst to be able to provide corrections to Norwegian names that should have been in Sámi, and vice versa, and the rest of the world, and Lule, and South.

Usage:

makeall.sh
lookup -flags mbTT words/dicts/smi/geo/bin/geo.fst

Meeting memos can be found at [http://giellatekno.uit.no/ped/index.html#Meeting+memos]

TODO

Corpus gathering

TODO:

Promoting Divvun

TODO:

Future plans, directions and ideas

See a separate document in plan/strat/5year.jspwiki.

Infrastructure

Børre has installed giza++, mosesdecoder, srilm, mkcl etc on the XServe, which will facilitate statistically based machine translation. There are experiments with the two ways of doing MT:

To accomodate future enhancements in different directions (in rough order of importance):

  1. test bench for all parts of our language technology efforts
    1. test bench enhanced, but not yet complet
  2. set up the Leopard Server features for collaborative support:
    1. permanent chat rooms
    2. stored (and indexed) chat transcripts of the chat rooms
    3. iCal server / group calendars
    4. wiki
  3. wiki? on G5 (is part of Leopard Server) or other web-based documentation
  4. improve Forrest stability and i18n support ( the divvun crashes)
    1. Sjur has been working on better i18n and pdf rendering
    2. Børre has some ideas for getting back to serving static html files
  5. reorganise the documentation:
    1. differ between target groups
    2. get better grouping
    3. decide what to write in forrest and what in wiki (cf. Apertium and [http://xixona.dlsi.ua.es/apertium/]) for a similar split)
    4. update/add missing parts
  6. migrate lexc lexicons to XML, splitting the task
    1. Name lexica (the Name project)
    2. Dictionaries (already in XML, task is to integrate them)
    3. At least migrate the lexc open POSes (Komi as a pilot case)
  7. change the look of the documentation web
  8. sfst?
    1. replacement for xfst -> see [omorf | http://www.ling.helsinki.fi/kieliteknologia/tutkimus/omor/index.shtml], omorf wiki and omorfi
    2. replacement for hunspell/open-source proofing tools
  9. investigate the NSIS installer, potentially replacing the InstallShield package from Polderland
  10. corpus content moved to Max Planck repositories? Norsk språkbank?
  11. update infrastructure to allow content-restricted spellers for special target groups

SVN issues:

SVN mail issue - solved.

TODO:

Linguistics

North Sámi

(nothing new, see proofing bugs below)

Lule Sámi

(nothing new, see proofing bugs below)

South Sámi

TODO:

Possible linguists to be invited:

Name lexicon/risten.no infrastructure

Instead of building our own webforms and back-end update scripts, use XForms with a premade connection to our xml db. Orbeon XForms is such a tool (open source).

From the meeting with the terminology and IT teams last week:

This means the following tasks:

TODO:

  1. fix i18n bug in risten.no/G5 (so they will work without the proper locale request) (Sjur)
  2. fix bugs in lexc2xml; add comments to the log element (Saara)
  3. finish first version of the editing (Sjur)
  4. test editing of the xml files. If ok, then: (Sjur, Thomas, Trond)
  5. make terms-smX.xml <=== automatically from propernoun-sme-lex.xml (add nob as well) (the morphological section should be kept intact, in e.g. propernoun-sme-morph.txt) (Sjur, Saara)
  6. convert propernoun-($lang)-lex.txt to a derived file from common xml files (Sjur, Tomi, Saara)
  7. implement data synchronisation between risten.no and the cvs repo, and possibly other servers (ie the G5 as an alternative server to the public risten.no - it might be faster and better suited than the official one; also local installations could be treated the same way)
  8. start to use the xml file as source file
  9. clean terms-sme.xml such that all names have the correct tag for their use (e.g. @type=secondary) (Thomas, linguists)
  10. merge placenames which are errouneously in different entries: e.g. Helsinki, Helsingfors, Helsset (linguists)
  11. publish the name lexicon on risten.no (Sjur)
  12. add missing parallel names for placenames (linguists)
  13. add informative links between first names like Niillas and Nils (linguists)

Dictionaries

Status: Ciprian has redone the makefile and the build process, generalized and standardised.

The scripts in gt/smX/testing/ should go to a more general and shared location.

The dictinary build command:

dicts$ make wordform_macdict S_LANG=sme T_LANG=nob

When will we have a Mac and PC dictionary to use and test? Wednesday.

Documentation (link below) must be written and translated, at least into Norwegian.

Tomcat, eXist are needed in order to make the dictionaries accessible on the web, as well as svn check-out and testing.

The www.divvun.no setup is appr 1 1/2 year old. The question is to what extent this setup will work with the present eXist version.

TODO:

Proofing tools

Hunspell

Børre did some investigations on compounding syntax - it does not look good.

TODO:

OpenXSpell

Working everywhere (almost) in MacOS X applications, provides Sámi spell checking system-wide through a hunspell back-end. OpenXSPell

There are two issues:

Another option could be CheckSpell. Seems to be more stable and developed. See [http://web.mac.com/heidi17/Heidikowa_witryna/CheckSpell.html].

Testing

Spelling Error Markup

TODO:

Speller testing

TODO:

Speller bugs

List of bugs returned from Polderland: 621, 630, 652, 656, 676.

Open issues based on test results:

sme

Version: Davvisámi, version 1.1, 2008-12-17

smj

Version: Julevsáme, version 1.1, 2008-12-17

TODO:

Hyphenator bugs

Open issues based on test results :

sme

Lexicon version: Davvisámi, version 1.1, 2008-12-17

smj

Lexicon version: Julevsáme, version 1.1, 2008-12-17

TODO:

Installer changes

TODO:

User documentation

TODO:

1.2 release

Content:

Other

Sámi week in Tromsø

Antti Suni is coming => meetings with at least Biret Ánne, Trond and Patrik Bye and Ove Lorentz. On Friday there will be a university strategy seminar - should somebody go there?

Schedule:

Text to speech

Antti has hinted at the possibility of doing beta versions of other languages as well. We are thus now recording Greenlandic sentences. A further possibility would be smj, sma, this would require phon-smX.xfst files for these languages as well (a couple of days’ work for smj, more for sma), plus recording.

TODO:

TNC, rikstermbanken and Sámi terms

It should be ok, but they need to send a formal request, to samediggi@samediggi.no. From there it will be forwarded to the relevant person.

Corpus contracts + open source

Postponed until the svn repository is fully functional (it is too open now).

Other issues

Next meeting, closing

The next meeting is 2.2.2009, 9.30 Norwegian time.

The meeting was closed at 11:56.

Appendix - task lists for the next five days

Boerre

Ciprian

David

Jovsset

Per-Eric

Maja

Saara

Sjur

Thomas

Tomi

Trond