Maltese Language Resource Server

Part of Speech Tagging in the MLRS Corpus (v3.0)

Part of speech (POS) tagging in the Korpus Malti v3.0 is carried out using SVMtool. Accuracy is at around 97%.

Below is a list of the tags which are used, along with a description for each one. These tags can be used to search for words and phrases in the third version of the MLRS Corpus (Korpus Malti v3.0 2016). A small-scale version of this corpus, the Korpus Malti v3.0 Lite, is also available.

ADJ
adjective
ADV
adverb
COMP
complementiser
CONJ-CORD
coordinating conjunction
CONJ-SUB
subordinating conjunction
DEF
definite determiner
FOC
focus particle
FUT
future particle
GEN
genitive particle
GEN-DEF
genitive particle with definite determiner
GEN-PRON
genitive particle with pronoun
HEMM
existential marker
INT
interjection
KIEN
auxiliary
LIL
oblique particle
LIL-PRON
oblique particle with pronoun
LIL-DEF
oblique particle with article
NEG
verbal negator
NOUN
noun
NOUN-PROP
proper noun
NUM-CRD
cardinal numeral
NUM-FRC
fraction
NUM-ORD
ordinal numeral
NUM-WHD
the number one (wie─žed and its inflections)
PART-ACT
active participle
PART-PASS
passive participle
PREP
preposition
PREP-DEF
preposition with article
PREP-PRON
preposition with pronoun
PROG
progressive particle
PRON-DEM
demonstrative pronoun
PRON-DEM-DEF
demonstrative pronoun with article
PRON-INDEF
indefinite pronoun
PRON-INT
interrogative pronoun
PRON-PERS
personal pronoun
PRON-PERS-NEG
negated personal pronoun
PRON-REC
reciprocal pronoun
PRON-REF
reflexive pronoun
QUAN
quantifier
VERB
verb
VERB-PSEU
pseudo verb
X-ABV
abbreviation
X-BOR
bordel
X-DIG
digit
X-ENG
English word
X-FOR
other foreign words
X-PUN
punctuation