Northern Sámi and Norwegian/release

From Apertium
< Northern Sámi and Norwegian
Revision as of 19:59, 28 July 2010 by Unhammer (talk | contribs) (that's testvoc that is)
Jump to navigation Jump to search

This page holds information about the release schedule for apertium-sme-nob.

Issues

High priority bad translations

What are the high-priority linguistic issues to deal with?

Would we gain a lot by inserting modals instead of adverbs for Pot/Cond verbs? Is there a better, general, way to translate the progressive? Should we get some of Francis' automatically discovered lex.sel rules? And are there any "simple" constructions that we could handle but don't yet?

  • TODO: Bidix will be added to with stuff from GTSVN
    • see dev/inc* (verbs need transitivity, nouns need gender checked, words with spaces shouldn't have)
  • TODO: After bidix additions, Francis will run apertium-lex-learner
  • TODO: URL recognition (I tried making some with lexc, it worked by itself, but took ages to compile into the regular lexc, not sure why)


  • DONE: Cond rules get modals, handled like passive in t1x (instead of "kanskje" in t3x), Pot gets "da<adv>" for now
  • DONE: In chunker/t1x, add tags to certain verbs (eg. using def-lists) that can be used in t3x to change/remove case-prepositions (see dev/valence.txt)
    • TODO: fill out with more def-list entries
    • TODO: go through dev/valence.txt and mark off which examples can be handled with noun-lists, and which with verb-lists
  • DONE: Insert epenthetics in compounds (nob.dix has n.*.sg.ind.cmp forms for all nouns, outputting the right epenthetic based on that)

TODO [1/2]: Multiple identical tags per reading in CG

  • DONE: Compounds mess up CG. We have to leave all the tags of the non-heads in because of bidix lookup, so we get eg. politiija<N><Sg><Nom><Cmp>+stašuvdna<N><Sg><Ill> (instead of politiija#stašuvdna<N><Sg><Ill> like the lookup2cg script gives). CG sees Nom and thus applies rules that it shouldn't, etc.
    • The ideal solution, but currently impossible: rename the non-head tags in BEFORE-/AFTER-SECTIONS. I tried BEFORE-SECTIONS SUBSTITUTE (N Sg Nom Cmp) (N* Sg* Nom* Cmp) which works for the above, but CG then also turns duohta<A><Sg><Nom><Cmp>+dilli<N><Sg><Acc> into duohta<A><@→N>+dilli<N*><Sg*><Nom*><Cmp><Sg><Gen>$, while if there are several non-heads, it'll only substitute in the first part. It seems some sort of tag order mechanism would be needed in CG for the BEFORE-SECTIONS/AFTER-SECTIONS stashing method to work.
    • It's possible to do the initial renaming in a twol rule (committed, but commented out for now), but we have no way of changing the tags back in CG (an AFTER-SECTIONS rule SUBSTITUTE N* N will unfortunately merge N* and later occurences of N).
    • Fix: cg-proc now ignores anything up until the last baseform, so given politiija<N><Sg><Nom><Cmp>+stašuvdna<N><Sg><Ill>, the rules will only see stašuvdna<N><Sg><Ill> (later we may have CG features to refer to the other sub-readings)
  • TODO: Derivations mess up CG. In lookup2cg, PoS tags are given stars if they appear before derivational tags. We could do this with twol, but again have no way of removing them before bidix. Also, the CG sub-reading features won't help here since we can't ignore _all_ tags up until the last derivation; say we have "lemma" V TV Der/n N Sg Ind, lookup2cg gives "lemma" V* TV Der/n N Sg Ind (leaving the TV tag intact).
    • Simple solution: lexicalise.
    • Boring solution: do the twol renaming to add stars to any PoS-before-derivation, and then move all the PoS tags into pardefs:
<pardef n="V" c="treat V* exactly like V for bidix lookup">
  <e>       <p><l><s n="V"/></l><r></r></p></e>
  <e r="LR"><p><l><s n="V*"/></l><r></r></p></e>
</pardef>
...
<e><p><l>gieldit<s n="TV"/></l><r>forby<s n="vblex"/><s n="pers"/></r></p><par n="V"/><par n="__verb"/></e>

DONE: remove unhandled derivations

Any derivations that are not handled we remove from the analyser with a twol negation rule in dev/xfst2apertium.useless.twol, this makes the lexicon a lot easier to handle for testvoc.

DONE: +G3 tag

This is used like the +Actor tag, for sme wsd (here based on "stadieveksling").

We move it after the +N tag in dev/xfst2apertium.hashtags.twol (so it gets the same position as +Actor), this makes transfer a lot simpler.

Getting a list of lemmas which have +G3 is easy (grep all nouns from bidix, analyse their lemmas and grep for lemma+G3), use this to tag bidix.

DONE: ensure we have all necessary postchunk rules

Postchunk rules are needed for any chunk containing a determiner/pronoun/adjective/noun/verb, we can easily make sure each possible chunk name has a postchunk rule (new chunks are created in t1x with names like pre_pre_nom, but may also be merged in t2x to eg. pre_pre_nom_conj_nom)

All possible SN and SA chunks should have the needed postchunk rules now.

Testvoc

Before release, we need to get testvoc out of the way – making sure there are no #'s and @'s in the output. As yet we don't have a way to create all possible surface forms from an HFST analyser, but we can at least run as large a corpus as we can find through sme-nob and look for # and @.

The script dev/sme-nob.inconsistency.sh tries to generate (with nob.dix) base forms (like infinitives or singular indefinites) of the various rhs entries in the bidix. Statistics so far:

Part-of-Speech entries from bidix that are OK in nob.dix in bidix but not in nob.dix comments in sme analyser but not bidix
verbs 14017 486 mostly mwe's missing ???
nouns 11635 238 some odd ones left ???
proper nouns 18935 26286 easy to find nob pardefs automatically ???
adverbs 235 1 ???
prepositions 42 0 :-) lots missing from bidix still
adjectives 1026 39 ???
abbreviations ??? ??? see dev/abbr.todo.dix 619
sub-/conjunctions 25 0

Schedule

Task Date
Work on high priority bad translations, expand bidix coverage until 2010-07-14
Remove unhandled derivations, ensure we have all postchunk rules 2010-07-14…2010-07-18
Testvoc 2010-07-18…2010-08-01
Tentative release date for apertium-sme-nob 0.1.0 August 1st 2010

Update: Lene and Trond have more free time after August, real release beginning of September?