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 10:13.

Present: Børre, Ciprian, Sjur, Thomas, Tomi, Trond

Absent: Maja (ill)

Agenda accepted as is.

Updated task status since last meeting

Børre

Ciprian

Maja

Sjur

Thomas

Tomi

Trond

Oahpa!

Bodø version as soon as Komi and Sma dictionaries are ready in a new version.

Finnish first, at best also other languages (a generalised multilingual Leksa).

This is the Bodø Oahpa!.

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

TODO

Corpus gathering

Now we have two scanners, as the book scanner arrived on Friday.

Which books are digitized?

TODO:

Promoting Divvun

TODO:

Future plans, directions and ideas

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

Northern areas project

TODO:

Infrastructure

HFST issues

To check out from svn:

svn co https://hfst.svn.sourceforge.net/svnroot/hfst/trunk hfstsvn

Remove all old Fink (/sw/) and MacPorts (/opt/) installations, then compile under Snow Leopard.

TODO:

VislCG 3

Everyone should have this one installed as well.

TODO:

Makefile + tag simplification

Present process:

  1. tailor the source files (remove lines containing SUB, GG, whatever)
  2. compile the tmp source files

Goal:

  1. compile the source files
  2. tailor the resulting transducer (subtract the strings containing SUB, GG, whatever)

Also replace xfst script files with -e “action” statements.

Old version:

iclock.fst: $(TARGET)/bin/iclock-$(TARGET).fst
$(TARGET)/bin/iclock-$(TARGET).fst: $(TARGET)/bin/clock-$(TARGET).fst
	@echo "*** iclock-$(TARGET).fst ***"
	@printf "load < $(TARGET)/bin/clock-$(TARGET).fst \n\
	invert net \n\
	save stack $@ \n\
	quit \n" >> tmp/iclock-script-$(TARGET)
	$(XFST) < tmp/iclock-script-$(TARGET)
	@rm -f tmp/iclock-script-$(TARGET)

New version:

iclock.fst: $(TARGET)/bin/iclock-$(TARGET).fst
$(TARGET)/bin/iclock-$(TARGET).fst: $(TARGET)/bin/clock-$(TARGET).fst
	@echo
	@echo "*** $(notdir $@) ***"
	@echo
	@$(XFST) -e "load < $<" \
			 -e "invert net" \
			 -e "save stack $@" \
			 -stop

TODO:

General list

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. iCal server / group calendars
    2. wiki
  3. wiki? on G5 (is part of Snow Leopard Server) or other web-based documentation
  4. improve Forrest stability and i18n support ( the divvun crashes)
  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. corpus content moved to Max Planck repositories? Norsk språkbank?
  9. update infrastructure to allow content-restricted spellers for special target groups

TODO:

Linguistics

North Sámi

(nothing new, see proofing bugs below)

Lule Sámi

(nothing new, see proofing bugs below)

South Sámi

Numerals:

Classification of pronouns etc:

  1. personal: manne “I”, dïhte “he/she/it”
  2. demonstrative: daate “this one”
  3. determiner: daennie gåetesne “to that house”

Personal vs demonstrative:

Anna Jacobsen: Dihte Kovlasaemiej åvtohke

Demonstrative vs. determiners

Here, we should have two paradigms, one pronominal +Pron+Dem, and one +Det, disambuguating to pre-nominal use.

Three types of problem areas:

We also seem to have problems with derivations:

jealadehtedh   jieliedehtedh	jieledh+V+Der1+Der/dehte+V+Inf
galmadehtedh   galmedehtedh	galmedidh+V+Der2+Der/ehte+V+Inf

TODO:

Name lexicon/risten.no infrastructure

Tomi has played with couchdb as a replacement for eXist in risten.no 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:

TODO:

  1. send eXist log files to Ciprian (Sjur)
  2. fix i18n bug in risten.no/G5 (so they will work without the proper locale request) (Sjur)
  3. fix bugs in lexc2xml; add comments to the log element (Saara)
  4. finish first version of the editing (Sjur)
  5. test editing of the xml files. If ok, then: (Sjur, Thomas, Trond)
  6. 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)
  7. convert propernoun-($lang)-lex.txt to a derived file from common xml files (Sjur, Tomi, Saara)
  8. 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)
  9. start to use the xml file as source file
  10. clean terms-sme.xml such that all names have the correct tag for their use (e.g. @type=secondary) (Thomas, linguists)
  11. merge placenames which are errouneously in different entries: e.g. Helsinki, Helsingfors, Helsset (linguists)
  12. publish the name lexicon on risten.no (Sjur)
  13. add missing parallel names for placenames (linguists)
  14. add informative links between first names like Niillas and Nils (linguists)

Dictionaries

Duplicated entries are now mostly removed, and much of the closed POS content copied from sme is now changed into sma. But the examples and their translations are still sme.

inc catalogue contains nouns.csv (2132 lines, 2030 unique nouns) and verb.csv (1701 lines, 1699 unique verbs). These should be diffed and added. Diff: 900 of the 2030 nouns and 1290 of the 1699 verbs are already in the smanob dictionary

TODO:

Proofing tools

South Sámi

TODO:

HFST-based proofing tools

Voikko will be our near future proofing solution, using HFST as the language technology core.

Please join the libvoikko mailing list.

One article linked:

[http://voikko.svn.sourceforge.net/viewvc/voikko/trunk/libvoikko/doc/morphological-analysis.txt]

TODO:

Testing

Spelling Error Markup

TODO:

Speller testing

TODO:

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:

Tag reordering for abbreviations have caused a lot of problems:

smj:
hr.
hr.	hr+ABBR+Acc
cand.philol.
cand.philol.	cand.philol+ABBR+N+Acc
Per
Per	Per+N+Prop+Mal+Sg+Attr

sme:
hr.
hr.	hr+N+ABBR+Acc
Per
Per	Per+N+Prop+Mal+Sg+Attr

Open issues based on test results:

sme

Version: Davvisámi, version 1.2, 2009-09-18

smj

Version: Julevsáme, version 1.2, 2009-09-20

TODO:

Hyphenator bugs

Open issues based on test results :

sme

Lexicon version: Davvisámi, version 1.2, 2009-09-18

No known issues!

smj

Lexicon version: Julevsáme, version 1.2, 2009-09-20

sma

Command to test the hyphenator:

preprocess dev/corp/pressemelding.txt | lookup bin/hyph-sma.fst | cut -f2 | \
lookup bin/hyphrules-sma.fst | grep -v '^$' | cut -f2 | uniq | see

TODO:

Installer changes

TODO:

User documentation

TODO:

1.2 release

Content:

Other

Spring planning

Topics:

Dates:

Text to speech

TODO:

MT and CAT

TODO:

Open source

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

TODO:

Christmas vacation / non-working days

SD: 24.12 and 31.12 are half days, and one of them off. One additional day in between is fully off.

UiT: all days in between are half days.

Who Days off
Børre off 30th and 31st
Ciprian no vacation planned, non-working on Christmas eve
Maja on sick leave the whole week before Christmas (21-24)
Sjur no vacation planned, non-working on Christmas eve
Thomas no vacation planned, non-working 28 and 31
Tomi no vacation planned
Trond off 23 (?), 24, leaving slightly earlier 21-22

Next meeting, closing

The next meeting is 28.12.2009, 9.30 Norwegian time.

The meeting was closed at 12:08.

Appendix - task lists for the next week

Boerre

Ciprian

Maja

Sjur

Thomas

Tomi

Trond