Language Technology at UiT The Arctic University of Norway

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

View GiellaLT on GitHub divvungiellatekno/

Page Content

Meeting setup


Cf. one of the following, depending on context:

Opening, agenda review, participants

Opened at 10:03.

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

Absent: none

Agenda accepted as is.

Updated task status since last meeting













A lot of feedback at the NoDaLiDa conference, especially on the use of speller technology. Interest in an Icelanding version.

Meeting memos can be found at []


Corpus gathering

Maja has called a couple of people (Nora Bransfjell, Åsta Vangberg, Anne-Lise Dunfjeld), they will send contracts to us. She will also send contracts to Ella Holm Bull, Bierna Bientie, Anne Grete Bientie

David has sent contracts to Sakka Nejne, Sara Aira Fjellström and the Sami School Board concerning the books: Ovmese Vaajesh and Sanna: Saemien-nïejte Johke-mehkeste. What about the Veaksehke Maarja book? David will send contract.

David has scanned the books Åarjelsaemien 1 and 2 leaving 3,4 and 5 to scan. Not yet completed proofreading the OCR:ed files.

Joseph has sent a formal letter from the Sami parliament to Gerd Persson regarding the possibility to incorperate her translation of the book Gåessie jeatjebh åerieminie to our corpus.

David has added more web texts from the swedish Sami Parlaments web page.

David has talked to Per-Stefan Labba at Saemien Ööhpehtimmiejarnge in Jokkmokk who gave permission to use the south sami version of Gulahalan. The book is not yet published, but the manuscript is ready.


Promoting Divvun


Future plans, directions and ideas

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

Northern areas project



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 []) 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. use HFST as alternative to XFST
  9. corpus content moved to Max Planck repositories? Norsk språkbank?
  10. update infrastructure to allow content-restricted spellers for special target groups



We need a more fine-grained system for denoting morphological boundaries. Here’s what Sjur suggests:

  1. word boundary: ## (# makes .#. unusable in twolc)
  2. inflection: <, >
  3. compound-like inflection: <#, #> (cf -gujmie) (lexc %<#, #%>)
  4. derivation: «, »
  5. compound-like derivation: «#, #» (cf -aktig, -skap in nob, swe, etc)
  6. clitica: ‹, › - muorak and muorage but only muorasge and not muorask
  7. opaque compounds (bringebær): *#, #* - * on the side of the opaque part

The multichar sequences should be defined as Multichar_Symbols.

It might be possible to distinguish, but do we need them?

the suffix -goahti- behaves:

Motivation for the new border symbols:

The guiding principle behind the symbols is that they provide more information in the transducer, and it is easy to discard the information later. The opposite is not true. Also, there is relatively little work involved in adding the symbols.

North Sámi

(nothing new, see proofing bugs below)

Lule Sámi

(nothing new, see proofing bugs below)

South Sámi

Maja, Thomas have worked a lot on adjectives. There are still many questions regarding the organisation of adjectives. The details will be discussed in the meeting tomorrow.

Adj->verb derivations is the next topic. Verb -> adj -derivations (some) already written in, tentatively. This topic probably needs more consideration than A -> V.


Name lexicon/ infrastructure

Tomi has played with couchdb as a replacement for eXist in and general dictionary-related work. Seems much lighter and easier to work with.

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:


  1. fix i18n bug in (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 and the cvs repo, and possibly other servers (ie the G5 as an alternative server to the public - 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 (Sjur)
  12. add missing parallel names for placenames (linguists)
  13. add informative links between first names like Niillas and Nils (linguists)


Nothing new, working hard on Kildin Sámi.


Proofing tools

HFST-based proofing tools

The tools do not compile easily on macs. We have a version of Htwolc on Sjurs mac, but nothing on Hlexc.

There is hope that HFST-based spellers can completely replace Hunspell in the long run. But there is a lot of work needed before we are there.




Børre has released beta7, with working clitics, negation verb and copula.


Spelling Error Markup


Speller testing


Testing open-source Norwegian spellers

Sjur has invited the open-source group to test their spell-checker using our test bench. The response has been positive, we’ll see what happens.

We should go to their developer meetings, and present our work and how to work with language technology.

Speller bugs

List of bugs returned from Polderland:

Open issues based on test results:


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


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


Hyphenator bugs

Open issues based on test results :


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


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


Installer changes


User documentation


1.2 release



Summer holidays

Person  Dates
Børre 06.07-26.07, 03.08-16.08
Ciprian 13.07.09-17.07.09 ???
Jovsset xx-yy
Maja week:27-31???
Sjur xx-yy
Thomas 130709-140809 ??
Tomi 28.05-14.06, ??
Trond 21.05-02.06. (travel), 29.06-yy ?? (first 3 july weeks) + before or after

South Sámi seminar follow-up

David sent the list to Sjur, who will have a look, and forward it to the travel agency.

Travelling plans in the coming months

Text to speech

To be started relatively soon. June?


MT and CAT

These are the next things forward. Two things to do before doing MT/CAT:

  1. Makefile redo
  2. xml transition of lexica

Open source

The repository is properly closed/open now, and the availability of the source code should be announced.


Short NoDaLiDa summary


Strong presense by our teams. A lot of interesting presentations, talks and papers: dependencies used in dictionaries and grammar checkers.

Lexicography article to LexicoNordica?

Background: Trond discussed with Ruth Vadtvedt Fjell about writing an article on Vuosttaš digisánit.

Next meeting, closing

The next meeting is 25.5.2009, 9.30 Norwegian time.

Trond will be away, but potentially available from his foreign location.

The meeting was closed at 11:45 .

Appendix - task lists for the next five days