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 10:03.

Present: Ciprian, Jovsset, Sjur, Thomas, Trond

Absent: Børre, Tomi

Agenda accepted as is.

Updated task status since last meeting

Børre

Ciprian

Jovsset

Lene

Per-Eric

Saara

Sjur

Thomas

Tomi

Trond

Pedagogical software online

Continuously making progress.

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

TODO:

Corpus gathering

Next step: Jovsset to call Sijti Jarnge for texts.

Could we get an updated list of Norwegian-Sámi place name pairs from Statens kartverk? Cf [http://yr.no], which is giving the correct weather forecast independent of which language the place name is written in, that is, they already have such a list. This will help the Ped project, and is useful to all of us. Thomas could look into this.

TODO:

Future plans, directions and ideas

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

Infrastructure

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 complete
  2. close certain parts of the svn code repository
    1. on the todo list
  3. more modularised make / build infra (prepare for smn, sms, sjd, others)
  4. merge gt, kt and st into one
  5. 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
  6. wiki? on G5 (is part of Leopard Server) or other web-based documentation
  7. 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
  8. 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 (http://www.apertium.org/ and http://xixona.dlsi.ua.es/apertium/) for a similar split)
    4. update/add missing parts
  9. 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)
  10. change the look of the documentation web
  11. sfst? Both as replacement for xfst and for hunspell/open-source proofing tools
  12. investigate the NSIS installer, potentially replacing the InstallShield package from Polderland
  13. corpus content moved to Max Planck repositories?
  14. update infrastructure to allow content-restricted spellers for special target groups

SVN issues:

TODO:

Linguistics

North Sámi

(nothing new, see proofing bugs below)

http://giellatekno.uit.no/bugzilla/show_bug.cgi?id=711

Lule Sámi

(nothing new, see proofing bugs below)

TODO:

South Sámi

TODO:

Name lexicon/risten.no infrastructure

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

September:

TODO:

Proofing tools

Hunspell

The conversion script runs out of memory and crashes. Børre is looking into alternative ways of doing the conversion.

TODO:

  1. change license on distros to GPL2+ (Børre)
  2. QA README and installation docs (Trond)
  3. fix the remaining conversion bugs (Børre, Tomi)

Testing

Spelling Error Markup

TODO:

Speller bugs

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

Open issues based on test results:

sme

Version: Davvisámi, version 1.0.1, 2008-06-02

smj

Version: Julevsáme, version 1.0.1, 2008-06-02

TODO:

Hyphenator bugs

Open issues based on test results :

sme

Lexicon version: Davvisámi, version 1.0.1, 2008-04-01

smj

Lexicon version: Julevsáme, version 1.0.1, 2008-04-01

TODO:

InDesign tools

Nothing new.

Releases

Support for new Microsoft Office suite in next release. We are waiting for new release to be available to subcontractors.

Within a month or so we will release a new version of the spellers, including support for the new Office version, and for Hunspell and aspell if feasible. Beyond improved MS Office version support, we should fix all known linguistic bugs as well.

TODO:

Other

Speech synthesis

Trond had a meeting last week with some relevant parties, and has made a first draft conversion from Sámi text to a Finnish-like transcription suitable for an online synthesis demo for Finnish.

cat text | preprocess | lookup -flags mbTT -utf8 bin/phon-sme.fst | cut -f2 | tr '\n' ' ' | see

Glue the result in here: [http://www.bitlips.fi/tts/demo.cgi]

Forthcoming Sámi allaskuvla conference

Info on the conference site.

Title submitted is: Goallosteapmi ja suorggideapmi Divvun-reaidduin

Registration: [http://www.viaregi.no/registration/deltagerweb.aspx?kid=3440&aid=8700]

Registration deadline is September 10.

Promoting Divvun

Jovsset’s neighbor is working at the ABC company, and didn’t know about the Divvun tools. Some sort of publicity or commercial for our tools within Sápmi is really needed. It is really important to reach the end users with information about the Divvun project.

TODO:

Forrest news

New Forrest component: OOo document out. Hopefully also vice versa (there is already a plugin that reads OOo documents).

Goal: Use an off-the-shelf Forrest (the latest, that is), instead of our own version of it.

The memory leak issue is still open, but we are hoping for progress. The workaround here is a restart script every 3rd minute. This script worked on the G5, but not on Linux.

Summer vacations

The Divvun team should report their vacation days to Julie. Thomas and Sjur done, Børre and Tomi todo.

Corpus contracts + open source

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

Next meeting, closing

The next meeting is 1.9.2008, 9.30 Norwegian time.

The meeting was closed at 11:41.

Appendix - task lists for the next five days

Boerre

Ciprian

Jovsset

Lene

Per-Eric

Saara

Sjur

Thomas

Tomi

Trond