UIT The arctic university of Norway > Giellatekno
 

Meeting_2006-10-30

Meeting setup

  • Date: 30.10.2006
  • Time: 09.30 Norw. time
  • Place: Where we are
  • Tools: SubEthaEdit, iChat

Agenda

  1. Opening, agenda review
  2. Reviewing the task list from two weeks ago
  3. Documentation - divvun.no
  4. Corpus gathering
  5. Corpus infrastructure
  6. Infrastructure
  7. Linguistics
  8. name lexicon infrastructure
  9. Spellers
  10. Other issues
  11. Summary, task lists
  12. Closing

1. Opening, agenda review, participants

Opened at 09: 45.

Present: Børre, Maaren, Saara, Sjur, Thomas, Tomi, Trond

Absent: none

Agenda accepted as is.

2. Updated task status since last meeting

Børre

  • contact writers who already have received contracts
    • Elle Márjá Vars and Aage Solbakk. Both said they would give us texts.
  • Move norwegian documents in Min Áigi from sme to nob
    • Not done
  • finish Forrest i18n work (pdf)
    • Fixed i18n in pdf together with Sjur. Cleaned up broken links.
  • cvs synching of the risten.no code in eXist (read-only)
    • Sjur did this
  • consider a script for automatic testing of the spell checker
    • Nothing done
  • consider more testing routines
    • Nothing done
  • update Maaren's Forrest installation to r430284
    • Not done
  • fix bugs!
    • Not done

Maaren

  • investigate the generated word form list sent to Polderland - use the command make pl-wordlist TARGET=sme in victorio
    • done some
  • investigate unrecognised word forms in the hyphenator
    • done some

Saara

  • add more texts to the graphical corpus interface
  • finalize server of the Xerox tools.
    • Paradigm generator implemented. final testing still going on. The text interface is working well, but there are some bugs in xml-version.
  • generate parallel corpus files manually (with Trond)
  • export corpus tools to location available to all (with cron), cf news disc.
    • not done.
  • help Trond with some shell commands
    • done some.
  • fix bugs!

Sjur

  • name lexicon:
    • refactor SD-terms editor code
      • done some more
    • implement missing propnouns editing functions
    • implement improvements decided upon in Tromsø
  • hire linguist and programmer
  • finish i18n work of Forrest
    • helped Børre with the PDF i18n
  • install our local copy of risten.no and propnouns on the G5
    • done
  • investigate unrecognised word forms in the hyphenator
  • decide how to specify compounding behaviour info in the lexicon
    • proposal posted to the news
  • fix bugs!
  • other:
    • participated in a Nordic language technology seminar in Gothenburg
    • cvs syncing of risten.no code on the G5 (with help from Børre)

Thomas

  • refine smj proper noun lexica, cf. the propernoun-smj-lex.txt
    • nothing this week
  • find and study all derived verbs in our corpus
    • nothing this week
  • suggest which derivations could be generated
    • nothing this week
  • investigate unrecognised word forms in hyphenator
    • done some serious investigations
  • investigate the generated word form list sent to Polderland - use the command make pl-wordlist TARGET=sme in victorio
    • done some serious investigations
  • decide how to specify compounding behaviour info in the lexicon
    • working on it
  • fix bugs!
    • worked

Tomi

  • continue implementation of the speller lexicon conversion
    • continued
  • make generator as server, based on Saara's code
    • Saara did
  • add lexc2xspell code to cvs
    • done
  • add hyphenation points to the generated output
    • not done
  • fix bugs!

Trond

  • refine smj proper noun lexica, cf. the propernoun-smj-lex.txt
    • Not done, haven't done more than saying "bures" to Thomas a couple of times.
  • Get more sma texts to improve language recognition
    • I got a whole bunch of texts, but lost my memory stick (!) More text is forthcoming, though.
  • study paragraphs with mixed content
    • Done some. There are systematic traits there, cf. discussion to come.
  • add corpus user accounts and access issues to Bugzilla
    • Not done.
  • investigate unrecognised word forms in the hyphenator
    • Don't remember this. Worked on sma hyphenator, though.
  • decide how to specify compounding behaviour info in the lexicon
    • Blank.
  • fix bugs!.

3. Documentation

One small problem: Forrest seems to crash on raw HTML. Børre will check it.

TODO:

  • finish i18n work (Børre and Sjur)
    • set up Tomcat at the faculty server, and install Forrest as war. Needs testing before being deployed on the server! Thus, install it on the G5 first and see that it works, then on the faculty server.
    • i18n does not work in PDF ("Table of Content" won't translate)
      • done - two strings still missing (we couldn't find their location)
  • check potential raw HTML bug/problem (Børre)

4. Corpus gathering

Two more authors contacted, both positive. Åge Solbakk is coming to Tromsø next week, Børre will meet with him then.

Børre has been digging more in the SD archives, and found some more texts.

sma

Inger Johansen found Trond's memory stick, we thus have some sma texts, and we will also get 200 000 words from Ove Lorentz (there is probably overlap). Bierna Bientie has been travelling this autumn, should be back this week, Trond will contact him for sma Bible texts.

smj

The Disamb project plans to have an smj week next week, and would very much like to have some more texts by then.

TODO:

  • continue to help NSI to get their corpus (Børre)
    • nothing last week, will visit them when going to Kautokeino this or next week
  • sma:
    • Bible (Trond).
    • Discussions with the Sámi Parliament (Børre, Sjur)
  • add as much smj texts as possible (Børre)

5. Corpus infrastructure

User accounts and access

TODO:

  • add the issue with subissues to Bugzilla (Trond)
    • not yet

More texts to the graphical corpus interface:

We have sent approximately 10 texts to Oslo, aligned and with sme analysis. Now, the nob texts must be analysed and the texts added to the interface. We will not send more texts now, but use these ones for testing.

TODO:

  • add text to the server (Lars)
    • Lars came back from holiday last week, which means it will probably soon be fixed

Aligner

TODO:

  • report improvements in aligner back to Øystein ( Børre)
  • gather more parallel texts (Trond)
  • try out NT alignment strategies (Saara)

Language recognition

Trond and Saara has done some work on paragraphs with mixed content.

Types of mixed paragraphs in the newspaper texts:

  1. Norwegian quotations (titles, repliques, etc.)
  2. Bilingual text, separated by some separator: (/)
  3. Systematic omissions in the original translations
  4. Technical text for the typographers
  5. Names
  6. Unsystematic Norwegian parts of sentences

Examples of the types:

  1. Muhtomin láve friddjavuođadovdu ja eará háve fas dakkár dovdu ahte "Dere tråkker faen ikke på meg lenger", logai Mari ovdalgo lávllestii maŋemus lávlaga ja konsearta lei ollislaš. ¶ Riikkaviidosaš aviisa Dagbladet lea jođihan dán iskkadeami. Logi eanemus liikojuvvon divttat leat earret eará Arnulf Øverland dikta «Du må ikke sove», ¶
  2. Vi har spurt eldre samer om hvordan de hadde det før i tiden./ Mii leat jearahallan vuorraset sápmelaččain mo sis lei bajásšattadettiin? ¶
  3. Du lihkkologut: 1, 14, 27 og 31 ¶
  4. BILDE: Kjell Kemi og Mai Britt Utsi ¶ HOVEDSAK: Bilde av Sponheim og rein ¶
  5. Eambbo dieđuid daid ortnegiid birra ja ohcanskoviid gávnnat min ruovttusiidduin, www.slf.dep.no - Økologisk. Sáhtát maid ságastit SLF: ain, Šaddobuvttadeami- ja ekologalaš eanadoalu ossodat, Seksjon planteproduksjon og økologisk landbruk. ¶
  6. 1992: s lei NSR sámi delegašuvnnas mii soabadii Justisministariin om opplegget for sedvanerettsundersoekelsen og folkerettsutredningen.

The first is the most common one. In the MÁ corpus, there are 4000 strings with quotations, 2500 of them with directed (left/right) quotations.

Suggestion for handling the types:

  1. Quoted strings: Pick out the quoted strings and check them separately
    1. when? preprocessor or conversion to XML? conversion to XML, see below
  2. Do nothing or look for known separators when the recognition returns alternatives? Safest approach: pessimistic - do nothing.
  3. Do nothing, and add "og" as a loan word in the lexicon (with !SUB!!!)
  4. Identify the technical words BILDE, HOVEDSAK, then mark them as non-wanted(?)
  5. Do nothing. (we go for CC "og")
  6. Do nothing for the time being (bilingual analysis in the future?)

Conversion of quotations:

<p lang=a>...dovdu ahte «Dere... » ...</p>
  -- converted to: --
<p lang=a>...dovdu ahte <span type="quote" lang="nb">«Dere... »</span> ...</p>

Types of quotations:

  • Directed: «», “”
  • Undirected: "" (if even number, easy, if odd, hard) <==

Norwegian sequences could be strung together, and treated as an un-analyzible part of the sentence.

Language distribution of paragraphs, as identified by the language recogniser:

LANG  # hits - reality:
sme   68431  - true
nob   10595  - true
smj    8468  - mostly sme, some smj
nno    1220  - mostly nob
eng     994  - true
fin     956  - some true, most sme?
dan     482  - false
ger     252  - false
sma      81  - mostly true, some short paragraphs may be false
isl       9  - false

TODO:

  • get more sma texts, first the Bible / NT (Trond)
  • add <span>to the corpus processing, encapsulating identifiable sequences of foreign language within them (Saara)

6. Infrastructure

Xerox tools wrapped as servers

Paradigm generator is now finished (some problems with the XML still). The server interface has changed, Tomis script needs to be updated.

Saara needs paradigm grammars for all POSes, see the example for N:

N+Subclass?+Number+Case+Possessive?+Clitic?
V+
A+
Adv+
Pron+
...

The inflector (generator as server) has four output options:

  1. short paradigm (nom, gen, gen pl)
  2. standard paradigm (full w/o poss and clitics)
  3. complete (incl poss. clitics)
  4. take any single string including tags, return inflected form

Input is one of:

  • Lemma + POS and grammar type (short / standard / complete)
  • Lemma + tag string

Next: add the hyphenation filter to the hyphenator server

TODO:

  • improve and finish the present prototype (Saara)
  • fix the corpus tag list in the cwb/ directory (Trond)
  • add the hyphenation filter to the hyphenator server (Saara)
  • create / check the paradigm grammar as exemplified above (Maaren)

Hyphenator

sma

Trond had some discussions with Ove Lorentz. We have done "maximize coda", he wants "maximize onset".

Unrecognised word forms

The unrecognised forms are forms generated by the nonrec transducer, but come out as question marks after going through the hyphenating transducer.

The command sequence is:

  1. log in to victorio, move to gt/
  2. make wordlist TARGET=sme (the result is: sme/wordlist-sme.txt.gz)
  3. move wordlist-sme.txt.gz to local computer (or G5?)
  4. make TARGET=sme (gives sme.fst)
  5. make hyph TARGET=sme (gives hyph-sme.fst)
  6. gunzip wordlist-sme.txt.gz
  7. cat wordlist-sme.txt
lookup -flags mbTT -utf8 bin/hyph-sme.fst > output.txt

TODO:

  • Update the sma hyphenator rule set with the insights gained from smj updates (Trond during weekends)
    • done several updates, still more to be done
  • investigate unrecognised word forms (Maaren, Thomas, Trond, Sjur)

M4

It is problematic for the CG rules, as the rule numbering gets mixed up. The hope is that it is possible to get the same effect in CG3. We still have no progress with CG3, though, but we will carry on the discussion with Odense.

7. Linguistics

Names and multilinguality

We need a more principled approach to this.

Background: the name lexicon is getting attention from the SD name/terminology sections, and they would like to use our name lexicon also for public searching.

Observations:

1) Multilinguality is always optional.

2) We can observe that "foreign" names in texts follows a domination pattern: majority language forms can be found in minority language texts as real names ("Kautokeino produkter"), whereas minority language names almost always occur in majority language texts as citations. And citations should not be considered a natural part of the text.

3) When looking at our name classification, multilinguality varies according to:

Ani - weak/none? (pet, myth anim.  names)
Fem - weak (informative)
Mal - weak (informative)
Obj - strong
Org - strong
Plc - strong for the national and country names, weak (informative) for foreign
       names
Sur - none
Tit - strong (titles)

Suggestion:

We need to reconsider the all names in all languages policy. That policy is valid only for Fem, Mal, and Sur (and Ani and Tit?). For Obj, Org, Plc the rule should be that if they have multilingual names, each name should only be used in it's own language. Then we need a modification saying that majority language names can be included in minority language lexicons if attested in our corpus. Also, the majority language varies according to country (obviously), which means that in a speller context, we might consider tailoring spellers for each country, leaving out noise relating to majority language names from another country.

A further issue is whether we should reconsider our cohort policy. Today, Sur and Plc are different readings. An alternative would be to have them as secondary tags, not in conflict with each other:

"<Trosterud>"
        "Trosterud" N Prop Sur Sg Nom <<< @HNOUN
        "Trosterud" N Prop Plc Sg Nom <<< @HNOUN
"<Trosterud>"
        "Trosterud" N Prop Sg Nom <Sur> <Plc> <<< @HNOUN
"<Trosterud>"
        "Trosterud" N Prop Sg Nom &Sur &Plc <<< @HNOUN

Derivation and spellers like Aspell

TODO:

  • find and study all derived words in our corpus (Thomas and Trond)
  • suggest which derivations could be generated (Thomas)
  • lexicalise the rest (Thomas)

North Sámi

Unwanted word forms:

  • comparation of -laš derivations (they should not be generated in comparative and superlative)

Questionable forms:

a-a     a-a+Interj
á-a     a-a+Interj  !SUB
ASDF:a  ASDF+N+ACR+Sg+Gen
A:a     A/S+N+ACR+Sg+Acc
f:a     f:a     +? (wanted: f Gen, f:s Loc)

from SGL meeting:
003/05: Davvisámegiela sánit normeremii 
(Gažaldagat leat boahtán divvun-prográmma ráhkadeddjiin)
1) 
Mot galgá merket oanádusaid sojaheami omd. NRK:as, NRKas, NRK-as?
Ovddeš Sámi giellaráđđi (Norggas) lea evttohan ná čállojuvvot:
	Nom.	NSR
	Akk.	NSR
	Gen	NSR`
Jearaldat lea, ahte galgatgo ain ná oanidit?
Mearrádus: 
Oanádusat sojahuvvojit dainna lágiin:
nom. 	NSR
 	Akk. 	NSR  (not NSR:a) <== a and NOT a:a
	Gen. 	NSR  <== a and NOT a:a
	Ill. 	NSR:i
	Lok.	NSR:s
	Kom.	NSR:in
	Ess.	NSR:n

Correct:
abstrávttabuinnán
abstrávttabuinnán       abstrákta+A+Comp+Sg+Com+PxSg1
abstrávttabuinnán       abstrákta+A+Comp+Pl+Loc+PxSg1

Error?
abstrávttaboiinnán
abstrávttaboiinnát
abstrávttaboiinnis
abstrávttaboiinniset
abstrávttaboiinnán
abstrávttaboiinnán      abstrávttaboiinnán      +?

**Dessa är med trots att dom är !SUB
***må taes bort!

accompagnerejun V+TV+Der/j+Pass+PrfPrc
ábuhuvvože      ábuhit+V+TV+Pass+Pot+Prs+Du1
áccohallagođežedne V+IV+Der/alla+Der/goahti+Pot+Prs+Du1


*en del var märkta !sub (med små bokstäver, av mej? Gör det nån skillnad?). Jag
har ändrat dom. Märkt dock att ovanstående INTE hade små bokstäver.

NB! SUB marking has to be with uppercase SUB to be removed.

TODO:

  • investigate the generated word form list sent to Polderland - use the command make pl-wordlist TARGET=sme in victorio ( Maaren, Thomas)
  • alphabet letters need to be correctly inflected (colon as case separator) ( Trond) this issue is already fixed and added to cvs.
  • check why some SUB-marked entries got included in the normative transducer ( Thomas, Sjur)
  • remove comparation from -laš derivations (Thomas, Sjur)

Lule Sámi

TODO:

  • refine smj proper noun lexica, cf. the propernoun-smj-lex.txt ( Thomas, Trond)
  • hire new linguist (Sjur)

8. Name lexicon infrastructure

Decided in Tromsø:

  • add logging facilities to the interface
  • add option to download local copies of the lexicon files directly from the db
  • batch editing (change all entries in the found set), should later be enhanced to allow selection of exceptions (the found set minus deselected items)
  • tag for excluding/including a name from certain applications
  • future epxansion: choose what info to display in the single language browser
  • display existing language entries when adding a new language to a record
  • add editor to change single, existing entries

Details can be found in the meeting memo.

TODO:

  • develop the needed XQueries and UI (Sjur, Tomi)
  • add the proper noun interface to the G5 (Sjur)
    • done, you can now try out the proper noun lexicon in risten.no.
  • cvs synching of the risten.no code in eXist (read-only) (Børre)
    • done
  • add a simple password protection to risten.no in the G5 (Børre)

Postponed:

  • data synchronisation between risten.no and the cvs repo
  • new version of xml2lexc (based on ccat), should handle complex names correct: construct entries like we have now from the different parts of a complex name entry

9. Spellers

Speller data generation

It reads the lexc files, communicates with the server, xml communication needs to be redone. No speller output yet, needs to be done by this week. It outputs the entries built by the conversion engine.

TODO:

  • add code to cvs (Tomi)
    • done
  • implement generator server based on Saara's code (Tomi)
    • done (by Saara)
  • decide how to specify compounding behaviour info for the lexicon ( Thomas, Trond, Sjur)
    • discussion started in news - please respond!
  • add hyphenation points to the generated output (Tomi)
  • planning meeting for the word form generator / data conversion script ( Sjur, Saara, Tomi)
    • discussion started in news

Automatic testing of the Word spellchecker

TODO:

  • consider a script for automatic testing (Sjur, Børre)
  • ask Polderland about testing tools (Sjur)
    • done
  • consider more testing routines (Sjur, Børre)
  • consider infra for testing feedback (Børre, Sjur)
  • get an Intel Mac for testing Windows spellers; get a WinXP license from SD ( Børre, Sjur)

10. Other

Bug fixing

64 open Divvun/Disamb bugs, and 24 risten.no bugs

Guess: 1/3 of the bugs are fixed already (?)

Task lists as iCal entries

Børre should have a look at Maaren's computer when he is in Kautokeino.

TODO:

  • update Maaren's Forrest installation to r430284 (Børre)

Employee seminar in Alta

SD has an employee seminar in Alta 7.-8. December - should we go there? Sjur will ask Julie Eira if we have to go there.

TODO:

  • ask Julie Eira about SD employee seminar (Sjur)

11. Next meeting, closing

Next meeting 6.11.2006 at 9: 30 (on the Swedish day in Finland - Swedish as the language, not the country: -) ).

Closed at 12: 14.

Appendix - task lists for the next week

Boerre

iCal

  • contact writers who already have received contracts
  • move norwegian documents in Min Áigi from sme to nob
  • consider a script for automatic testing of the spell checker in Word
  • consider more testing routines
  • update Maaren's Forrest installation to r430284
  • check potential raw HTML bug/problem
  • sma discussions with SD (with Sjur, Trond)
  • add as much smj texts as possible
  • report improvements in aligner back to Øystein
  • add a simple password protection to risten.no in the G5
  • consider infra for testing feedback
  • get an Intel Mac for testing Windows spellers; get a WinXP license from SD
  • fix bugs!

Maaren

iCal

  • investigate the generated word form list sent to Polderland - use the command make wordlist TARGET=sme in victorio
  • investigate unrecognised word forms in the hyphenator
  • create / check the paradigm grammar as exemplified above

Saara

iCal

  • add more texts to the graphical corpus interface
  • finalize server of the Xerox tools.
  • improve text_cat with paragraphs of mixed content
  • generate parallel corpus files manually (with Trond)
  • export corpus tools to location available to all (with cron), cf news disc.
  • help Trond with some shell commands
  • plan the word form generator / data conversion script
  • add <span>to the corpus processing, encapsulating identifiable sequences of foreign language within them
  • fix bugs!

Sjur

iCal

  • name lexicon:
    • refactor SD-terms editor code
    • implement missing propnouns editing functions
    • implement improvements decided upon in Tromsø
  • hire linguist and programmer
  • finish i18n work of Forrest with Børre
  • investigate unrecognised word forms in the hyphenator
  • decide how to specify compounding behaviour info in the lexicon
  • sma discussions with SD (with Børre, Trond)
  • check why some SUB-marked entries got included in the normative transducer
  • remove comparation from -laš derivations
  • plan the word form generator / data conversion script
  • consider a script for automatic testing of the spell checker in Word
  • consider more testing routines
  • consider infra for testing feedback
  • get an Intel Mac for testing Windows spellers; get a WinXP license from SD
  • ask Julie Eira about SD employee seminar
  • fix bugs!

Thomas

iCal

  • refine smj proper noun lexica, cf. the propernoun-smj-lex.txt
  • find and study all derived words in our corpus (with Trond)
  • suggest which derivations could be generated
  • investigate unrecognised word forms in hyphenator
  • decide how to specify compounding behaviour info in the lexicon
  • check why some SUB-marked entries got included in the normative transducer
  • remove comparation from -laš derivations
  • fix bugs!

Tomi

iCal

  • continue implementation of the speller lexicon conversion
  • make generator as server, based on Saara's code
  • add lexc2xspell code to cvs
  • add hyphenation points to the generated output
  • plan the word form generator / data conversion script
  • fix bugs!

Trond

iCal

  • refine smj proper noun lexica, cf. the propernoun-smj-lex.txt
  • get more sma texts, first the Bible / NT
  • add corpus user accounts and access issues to Bugzilla
  • fix the corpus tag list in the cwb/ directory
  • investigate unrecognised word forms in the hyphenator
  • decide how to specify compounding behaviour info in the lexicon
  • sma discussions with SD (with Børre, Sjur)
  • find and study all derived words in our corpus (with Thomas)
  • fix bugs!.