Latvian part-of-speech tagset

A tagset is a list of part-of-speech tags (POS tags for short), i.e. labels used to indicate the part of speech and sometimes also other grammatical categories (case, tense etc.) of each token in a text corpus.

Latvian part-of-speech tagset is available in Latvian corpora annotated by the LV Tagger for Latvian developed by the Artificial Intelligence Laboratory of the University of Latvia, Institute of Mathematics and Computer science Machine learning code based on the Stanford NLP kit. The used tagset is derived from MULTEXT-East morphological specification and it is very close to this tagset format.

Latvian

available corpora

An Example of a tag in the CQL concordance search box: [tag="ncfsg4"] finds all common feminine singular nouns in genitive of 4th declension, e.g. pilsētas, mājas (note: please make sure that you use straight double quotation marks)

General part-of-speech tagset classification

noun	n.*
verb	v.*
adjective	a.*
pronoun	p.*
adverb	r.*
adposition	s.*
conjunction	c.*
numeral	m.*
particle	q.*
interjection	i.*
abbreviation	y
residual	x.*
punctuation	z.*

Noun

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Noun	n
1	Type	common	c
		proper	p
		not applicable	_
2	Gender	masculine	m
		feminine	f
		not applicable	_
3	Number	singular	s
		plural	p
	Number-special	always plural	d
	Number-special	always singular	v
		not applicable	_
4	Case	nominative	n
		genitive	g
		dative	d
		accusative	a
		vocative	v
		locative	l
	case-special	genitive only	s
		not applicable	_
5	declension	1	1
		2	2
		3	3
		4	4
		5	5
		6	6
		reflexive	r
		not applicable	0

Verb

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Verb	v
1	Type	main	m
		modal	o
		Auxiliary ‘to be’	c
		Auxiliary ‘become’	t
		Requires genitive – ‘not be’, ‘lack’, ‘have-enough’	g
		phasal	p
		expression	e
		not applicable	_
2	Reflexive	yes	y
		no	n
		not applicable	_
3	Mood	participle	p
		indicative	i
		future	f
		infinitive	n
		conditional	c
		debitive	d
		imperative	m
		relative	r
		not applicable	_
4	Tense	present	p
		past	s
		future	f
		not applicable	0
5	Transitivity	transitive	t
		intransitive	i
		not applicable	0
6	Conjugation	1	1
		2	2
		3	3
		irregular	r
		not applicable	0
7	Person	1	1
		2	2
		3	3
		not applicable	0
8	Number	singular	s
		plural	p
		not applicable	0
9	Voice	active	a
		passive	p
		not applicable	0
10	Negation	yes	y
		no	n
		not applicable	0

Adjective

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Adjective	a
1	Type	relative	r
		qualificative	f
		not applicable	_
2	Gender	masculine	m
		feminine	f
		not applicable	_
3	Number	singular	s
		plural	p
		not applicable	_
4	Case	nominative	n
		genitive	g
		dative	d
		accusative	a
		vocative	v
		locative	l
		not applicable	_
5	Definiteness	indefinite	n
		definite	y
		not applicable	_
6	Degree	positive	p
		comparative	c
		superlative	s
		not applicable	_

Pronoun

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Pronoun	p
1	Type	personal	p
		demonstrative	d
		indefinite	i
		possessive	s
		interrogative	q
		relative	r
		reflexive	x
		definite	g
		not applicable	_
2	Person	1	1
		2	2
		3	3
		not applicable	0
		not applicable	_
3	Gender	masculine	m
		feminine	f
		not applicable	0
		not applicable	_
4	Number	singular	s
		plural	p
		not applicable	0
		not applicable	_
5	Case	nominative	n
		genitive	g
		dative	d
		accusative	a
		locative	l
		not applicable	_
6	Negation	no	n
		yes	y
		not applicable	_

Adverb

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Adverb	r
1	Degree	positive	p
		comparative	c
		superlative	s
		relative	r
		not applicable	0
		not applicable	_
2	type	time	t
		manner	m
		place	p
		quantative	q
		causative	c
		not applicable	_

Adposition

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Adposition	s
1	Type	preposition	p
		postposition	t
		not applicable	_
2	Number	singular	s
		plural	p
		not applicable	_
3	Case	genitive	g
		dative	d
		accusative	a
		not applicable	_
4	Usable as location adverb	yes	y
		no	n
		not applicable	_

Conjunction

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Conjunction	c
1	Type	coordinating	c
		subordinating	s
		not applicable	_
2	Structure	compound	c
		double	d
		simple	s
		not applicable	_

Numeral

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Numeral	m
1	Type	cardinal	c
		ordinal	o
		fraction	f
		not applicable	_
2	Structure	compound	c
		simple	s
		conjuction	c
		not applicable	_
3	Gender	masculine	m
		feminine	f
		not applicable	0
4	Number	singular	s
		plural	p
		not applicable	_
5	Case	nominative	n
		genitive	g
		dative	d
		accusative	a
		locative	l
		not applicable	0
6	Numeral order	ones	v
		teens	p
		tens	d
		hundreds	s
		thousands	t
		millions	m
		billions	r
		not applicable	_

Particle

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Particle	q
1	Type	compound	c
		simple	s
		not applicable	_

Interjection

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Interjection	i
1	Type	compound	c
		simple	s
		not applicable	_

Abbreviation

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Abbreviation	y

Residual

P	Attribute (en)	Value (en)	Code
0	CATEGORY	Residual	x
1	type	URL	u
		numeral	n
		ordinal number	o
		other	x
		typo	t
		foreign word	f

Source: https://github.com/PeterisP/morphology/blob/master/src/main/resources/TagSet.xml (formal XML tagset notation)

Reference

P. Paikens, L. Rituma, L. Pretkalnina. Morphological analysis with limited resources: Latvian example. In Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA), 2013. (PDF)

Full tagset summary