The Second Swiss Estonian Workshop on Computational and Theoretical Linguistics

Training a tagger for Estonian

The tagset

Nouns

NN      noun
NNP     proper noun

Adjectives

AA      attributive adjective (positive)
AAC     attributive adjective (comparative)
AAS     attributive adjective (superlative)

AP      predicative adjective (positive)
APC     predicative adjective (comparative)
APS     predicative adjective (superlative)

Adverbs

ADV     adverb (positive)
ADVC    adverb (comparative)
ADVS    adverb (superlative)

Adpositions

APPO    postposition
APPR    preposition

Numbers

NUM     number
NUMSP   number (spelled out)

Conjunctions

KOS     subordinating conjunction
KOC     coordinating conjunction
KOCOM   comparing conjunction

Pronouns

PPER    personal pronoun
PPOS    possessive pronoun
PREF    reflexive pronoun
PD      demonstrative pronoun
PREL    relative pronoun
PI      indefinite pronoun
PW      question pronoun

Particles

PTKV    verbal particle
PTKA    superlative particle (kõige)
PTKQ    question particle (kas)
PTKI    imperative particle 

Verbs

VFINF   full verb (infinite)
VFPP    full verb (participle)
VFFIND  full verb (declarative)
VFFINC  full verb (conditional)
VFFINQ  full verb (quotative)
VFFINI  full verb (imperative)

VAINF   auxiliary (infinite)
VAPP    auxiliary (participle)
VAFIND  auxiliary (declarative)
VAFINC  auxiliary (conditional)
VAFINQ  auxiliary (quotative)
VAFINI  auxiliary (imperative)

VMINF   modal (infinite)
VMPP    modal (participle)
VMFIND  modal (declarative)
VMFINC  modal (conditional)
VMFINQ  modal (quotative)

Odds and Ends

ABBR    abbreviation
FM      material of a foreign language
ITJ     interjection
TRUNC   truncation
XY      non-word

Punctuation

-      dash                  -
C      comma                 ,
Co     colon                 :
Ex     exclamation mark      !
LI     list item             * - 
P      paragraph
Pc     parenthesis closed    )
Po     parenthesis opened    (
Q      question Mark         ?
QM     quotation mark        "
S      full stop             .
Se     semicolon             ;
SSS    three dots            ...


Author: Beat Vontobel (bvontob@cl.unizh.ch)
Date of last modification: June 27, 1997