S O U T H   S Á M I   D I S A M B I G U A T O R

On this page

• Delimiters, tags and sets
  • Tags
    • BOS/EOS:
    • Morphological tags
    • Derivation tags
    • Error usage tags
    • Other tags
    • Semantic tags
    • Secondary tags
    • Syntactic tags
    • Titles
• Sets
  • Sets of morphological tags for syntactic use
  • Noun sets
  • Verb sets
  • Adjective sets
  • Adverb sets
  • Postposition sets
  • BOUNDARY SETS
  • Derivation sets
• Guessing: Rule for adding Adv Sem/Adr as a tag to readings which looks addresses
• Guessing: Rule for adding Adv Sem/Adr as a tag to readings which looks addresses
• N or V
• Cycle 0 (Early rules)
  • Numerals and ACR
  • Numerals in QPs
  • CC og not (spesifikke regler lenger ned)
  • Interj
  • Possessive suffix
  • Pronouns
  • Proper nouns
  • Verbs
  • Postpositions
  • Particles and adverbs
  • Adjective or Indef
  • First names (Surnames)
  • Demonstratives
  • Genitive
  • Adjective or not
  • Adverbs
  • Verbs
• Mapping rules
  • CC- and CS-Mapping
• CNP mapping
• CC and CS or Adv (have to be before CVP rules)
• CVP Mapping
• PrfPrc
  • (@A<) target Inf
  • killifVinCohort
• Person
• Span sentences
  • Nomen
  • Verb or Noun
• Adj or Adv
• Grammatisk ord eller N eller A
• N or V

S O U T H   S Á M I   D I S A M B I G U A T O R

Delimiters, tags and sets

"<.>" "<!>" "<?>" "<...>" "<¶>" sent

Tags

BOS/EOS:

• (>>>) (<s>)
• (<<<) (</s>)

Morphological tags

• N
• Sg Pl

• Nom Acc Gen Ine Ela Ill Com Ess

• PxSg1 PxSg2 PxSg3 PxPl1 PxPl3 PxPl3

• Sg1 Sg2 Sg3 Pl1 Pl2 Pl3 ;

Derivation tags

• Der/A
• Der/Car
• Der/Dimin
• Der/InchL
• Der/NomAct
• Der/NomAg
• Der/PassL
• Der/PassS
• Der/Rec
• Der/adte
• Der/ahtje
• Der/alla
• Der/d
• Der/eds
• Der/ht
• Der/htalle
• Der/htj
• Der/ihks
• Der/ijes
• Der/l
• Der/laakan
• Der/ldahke
• Der/ldh
• Der/ldihkie
• Der/les
• Der/lg
• Der/st
• Der/vuota

Error usage tags

We define two lists for Err/xxx tags:

• Err/Orth:
  • Err/Orth
  • Err/Orth-a/á
  • Err/Orth-nom/gen
  • Err/Orth-nom/acc
  • Err/DerSub
  • Err/CmpSub
  • Err/UnspaceCmp
  • Err/HyphSub
  • Err/SpaceCmp
  • Err/Spellrelax
  • err_orth_mt
• Err/Orth-spes:
  • Err/Orth-a/á
  • Err/Orth-nom/gen
  • Err/Orth-nom/acc
  • Err/DerSub
  • Err/CmpSub
  • Err/UnspaceCmp
  • Err/HyphSub
  • Err/SpaceCmp
  • Err/Spellrelax
  • err_orth_a_á_mt
  • err_orth_nom_acc_mt
  • err_orth_nom_gen_mt

Other tags

• Cmp/Hyph
• <vdic>

Semantic tags

Secondary tags

Syntactic tags

• @CNP @CVP @+FAUXV @+FMAINV @-FAUXV @-FMAINV MAINV =

Titles

REAL-TITLE OFFICE TITLE

Sets

Sets of morphological tags for syntactic use

CASES ADVLCASE NUMBER

Noun sets

INSTITUTION ORGANIZATION EDUCATION CURRENCY CURRENCY LESSON

Verb sets

REALCOPULAS

COPULAS

V-NOT-COP

MOD-ASP

VFIN-NOT-IMPRT

Adjective sets

Adverb sets

GUKTIEGOSSE

DAESTIE

ILLADV

INEADV1

ELAADV1

INEADV

ELAADV

DV-MOD-ADV

Postposition sets

ILLPO

BOUNDARY SETS

REALCLB

SV-BOUNDARY

NP-BOUNDARY

Derivation sets

V-DER

V-DER-SUF

N-DER N-DER-SUF

A-DER A-DER-SUF

PASS

LEX-V LEX-N LEX-A LEX-ADV

VERB-FORMS 2-PERS

Disambiguation rules

BEFORE-SECTIONS

Rule for adding Sem/Date as a tag to readings which looks like dates (fjernes når vi får felles numeralfil fra shared)

Guessing: Rule for adding Adv Sem/Adr as a tag to readings which looks addresses

Guessing: Rule for adding Adv Sem/Adr as a tag to readings which looks addresses

Rules for adding to verbs denoting verbal actions like: ... jeahta Aili Kestkitalo.

N or V

SECTION

Cycle 0 (Early rules)

Removing non-lexicalised forms when lexicalised

• derHderAlla, derAlla, derH, derST chosses longest Der/tag

Numerals and ACR

Numerals in QPs

CC og not (spesifikke regler lenger ned)

Interj

Possessive suffix

REmove Px if not family

Pronouns

Proper nouns

INITIAL

• PropInsideProp Selects Prop if capital letter inside clause

Verbs

Postpositions

Selecting postpositions when preceded by genitives, etc.

Particles and adverbs

Adjective or Indef

First names (Surnames)

• PropAttr1 Selects Attr if you are Sem/Fem OR Sem/Mal, Sem/Sur or INITIAL and to your right is Prop which is Sem/Fem OR Sem/Mal or Sem/Sur

Demonstratives

Genitive

Adjective or not

Rel or Interr OR Indef

Adverbs

Selecting adverbs in local contexts

Verbs

Selecting verbs in local contexts, based upon agreement patterns

Selecting imperative sentence-initially with appropriate right context

Remove verb readings

Select Inf

Mapping rules

CC- and CS-Mapping

• COMPCS @COMP-CS< to Adv or A after goh etc.

• CSasCNPCVP Map some CSs both @CNP @CVP

CNP mapping

Mapping CNP to CC and CS.

CC and CS or Adv (have to be before CVP rules)

CVP Mapping

Mapping @CVP to all CS

Attributes or not

PrfPrc

Select PrfPrc if DerNomAct

Mapping verbs

(@A<) target Inf

• AInf Inf

• SUBJ>Inf

killifVinCohort

This rule removes all other readings, if there is a mapped V reading in the same cohort. Every case which this goes wrong, should be fixed in mapping rules or previous disrules.

Person

leah Prs Sg2 = Pl3

Select Inf If Infv

Span sentences

Nomen

Remove Prop Attr if not 1 Prop

Verb or Noun

Adj or Adv

Grammatisk ord eller N eller A

N or V

Ger or Der/NomAct

Adj or Indef

Num

Adv or Po/Pr

Illative or genetive

Essive

Comitative

• SgCom and Ess removes Sg Com and Ess when BIEHKIE

Accusative or illative

Indef or Adv

special lemmas

Adverb context prefers Adv

Verb person vs. Inf – moved here in order to have the pronouns disambiguated first.

Proper nouns

Rule set taken from sme

gellie as numeral, not pronoun

---

This (part of) documentation was generated from src/cg3/disambiguator.cg3