Lithuanian UPOS XPOS NER DEP

UPOS (Universal POS)

UPOS (Universal Part-of-Speech) tags are a core component of the Universal Dependencies (UD) project, designed to provide a standardized, fixed set of 17 categories that remain consistent across all human languages. Unlike language-specific systems (XPOS), which reflect the unique morphological intricacies of a single tongue, UPOS focuses on the functional role of a word. By stripping away language-specific "noise," UPOS allows researchers and developers to compare syntactic structures cross-linguistically and facilitates Cross-Lingual Transfer Learning—where an AI model trained on one language (like English) can apply its structural knowledge to another (like Romanian or Korean). It essentially serves as a "Lingua Franca" for computational linguistics, ensuring that a NOUN remains a NOUN whether the underlying grammar is agglutinative, fusional, or analytic.

Try our Lithuanian UPOS tagging now.

UPOS Universal Part-of-Speech
Group	Tag	Meaning	Example
Open Class	ADJ	Adjective	didelis, senas, žalias, nesuprantamas, pirmas
	ADV	Adverb	labai, rytoj, žemyn, kur, ten
	INTJ	Interjection	pst, ai, bravo, labas
	NOUN	Noun (common)	mergaitė, katė, medis, oras, grožis
	PROPN	Proper Noun	Marija, Jonas, Londonas, NATO, HBO
	VERB	Verb	bėgti, bėga, bėgantis, valgyti, valgė, suvalgytas
Closed Class	ADP	Adposition	į, pas, metu
	AUX	Auxiliary	yra, turi (padaręs), darys, turėtų
	CONJ	Conjunction	ir, arba, bet (pasenusi žymė)
	CCONJ	Coordinating Conjunction	ir, arba, bet
	SCONJ	Subordinating Conjunction	jei, kol, kad
	DET	Determiner	—, —, —
	NUM	Numeral	1, 2017, vienas, septyniasdešimt septyni, MMXIV
	PART	Particle	—, ne
	PRON	Pronoun	aš, tu, jis, ji, aš pats, jie patys, kažkas
Other	PUNCT	Punctuation	., (, ), ?, ]
	SYM	Symbol	$, %, +, −, :), 🐻
	X	Other / Foreign	sfpksdpsxmsa, ..., foreign words
	SPACE	Space	newlines, tabs, extra spaces

XPOS (Detailed POS)

XPOS (Language-Specific Part-of-Speech) tagging offers a much higher level of granularity than the broader UPOS (Universal Part-of-Speech) system. While UPOS provides a standardized set of labels designed to work consistently across every language—ensuring that a NOUN in English is treated similarly to a NOUN in XPOS preserves the unique "linguistic DNA" of a specific language. It is the engine behind complex morphological analysis, allowing a system to distinguish not just that a word is a "Verb," but specifically that it is a "Third-Person, Singular, Past Tense, Passive Voice" verb. By capturing the deep grammatical details that UPOS omits for the sake of universality, XPOS enables the creation of translation tools and parsers that understand the precise inflectional logic of a specific culture and tongue.

Lithuanian follows the standard Baltic linguistic tradition of packing every inflectional feature into the string. The tags are hierarchical: they start with the Part of Speech (e.g., vksm. for verb) and move through specific sub-categories like mood (tiesiog.), tense (būt-k.), and finally person or case markers. This system, often referred to as the JTE or ALKSNIS tagset, distinguishes between proper and common nouns, active and passive voices, and even neuter genders in adjectives and participles.

Try our Lithuanian XPOS tagging now.

Lithuanian xpos morphological detail
Category	Abbreviation	Lithuanian Term	English Meaning	Example
Core POS	dkt. / dktv.	Daiktavardis	Noun	namas
	vksm.	Veiksmažodis	Verb	eiti
	bdvr.	Būdvardis	Adjective	geras
	sktv.	Skaitvardis	Numeral	penki
Sub-type	tikr.	Tikrinis	Proper (Noun)	Lietuva
Sub-type	bendr.	Bendrinis	Common (Noun)	miestas
Gender	vyr.	Vyriškoji giminė	Masculine	jis
	mot.	Moteriškoji giminė	Feminine	ji
	bev.	Bevardė giminė	Neuter	gera (it is good)
Verb Form	asm.	Asmenuojamoji	Finite / Personal	dirbu
	dlv.	Dalyvis	Participle	einantis
	pusd.	Pusdalyvis	Half-participle	eidamas
	pad.	Padalyvis	Gerund	einant
	bndr.	Bendratis	Infinitive	eiti
Mood & Voice	tiesiog.	Tiesioginė nuosaka	Indicative	dirba
	tar.	Tariamoji nuosaka	Subjunctive / Conditional	dirbtų
	liep.	Liepiamoji nuosaka	Imperative	dirbk!
	veik.	Veikiamoji rūšis	Active Voice	skaitantis
	neveik.	Neveikiamoji rūšis	Passive Voice	skaitomas
Tense	es.	Esamasis laikas	Present	skaito
	būt-k.	Būtasis kartinis laikas	Past (Simple)	skaitė
	būt-d.	Būtasis dažninis laikas	Past Iterative	skaitydavo
	būs.	Būsimasis laikas	Future	skaitys
Case	V.	Vardininkas	Nominative	-
	K.	Kilmininkas	Genitive	-
	N.	Naudininkas	Dative	-
	G.	Galininkas	Accusative	-
	Įn.	Įnagininkas	Instrumental	-
	Vt. / Viet.	Vietininkas	Locative	mieste
	Š.	Šauksmininkas	Vocative	drauge!
Other	vns.	Vienaskaita	Singular	-
	dgs.	Daugiskaita	Plural	-
	1, 2, 3	Asmuo	1st, 2nd, 3rd Person	-
	sngr.	Sangrąžinis	Reflexive	mokytisi
	įvardž.	Įvardžiuotinis	Pronominal (Definite)	baltojis

Dependency

The DEP (Syntactic Dependency) refers to the specific grammatical relationship between a "child" token and its "head" (parent) token. While primary labels (like nsubj or obj) describe the basic structure, attachments starting with a colon (:) provide fine-grained sub-type information. For instance, while nsubj identifies a subject, :pass refines this to show the subject is being acted upon (Passive Voice). Similarly, :nn (Noun Compound) or :assmod (Associative Modifier) help the parser distinguish between simple modifiers and complex ownership or compound relationships, allowing for a much deeper "logical" understanding of the sentence.

DEP Full Syntactic Dependency Labels
Category	Label	Meaning	Example (Token in bold)
Core Arguments	nsubj	Nominal subject	Elonas valgo.
	csubj	Clausal subject	Tai, ką jis padarė, buvo neteisinga.
	obj	Direct object	Matau mėnulį.
	iobj	Indirect object	Ji davė man dovaną.
	ccomp	Clausal complement (finite)	Jis pasakė, kad yra pavargęs.
	xcomp	Open clausal complement	Noriu eiti.
Non-Core Dependents	obl	Oblique nominal	Jis atsisėdo ant kėdės.
	vocative	Vocative	Jonai, ateik čia!
	expl	Expletive	Ten yra katė.
	dislocated	Dislocated element	Pažįstu tą vyrą.
	advcl	Adverbial clause modifier	Išėjau, kai jis atvyko.
	advmod	Adverbial modifier	Bėk greitai.
	discourse	Discourse element	Na, nesu tikras.
	aux	Auxiliary	Galiu matyti.
	cop	Copula	Ji yra laiminga.
	mark	Subordinating marker	Žinau, kad tu žinai.
Nominal Dependents	nmod	Nominal modifier	Automobilio durys.
	appos	Appositional modifier	Semas, mano draugas.
	nummod	Numeric modifier	Septynios dienos.
	acl	Adjectival clause	Planas laimėti.
	amod	Adjectival modifier	Mėlynas dangus.
	det	Determiner	Pabaiga.
	case	Case marking	Prancūzijos karalius.
	fixed	Fixed multiword expression	Nepaisant to.
	flat	Flat multiword name	Niujorko miestas.
	compound	Compound noun	Telefono būdelė.
	list	List element	Telefonas, raktai, piniginė.
Coordination	conj	Conjunct	Duona ir sviestas.
Coordination	cc	Coordinating conjunction	Duona ir sviestas.
Special Labels	aux:pass	Passive auxiliary	Jis buvo pavogtas.
	punct	Punctuation	Labas!
	dep	Unspecified dependency	(Naudojama nežinomoms nuorodoms)
	ROOT	Root of the sentence	Aš valgiau pietus.

Common Dependency Attachments (Sub-labels)
Attachment	Full Name	Explanation	Example
:pass	Passive	Indicates a relationship in a passive voice construction.	nsubj:pass (Langas buvo išdaužtas)
:nn	Noun Compound	Indicates that a noun is modifying another noun in a compound structure.	compound:nn (Telefono įkroviklis)
:prep	Prepositional	Refines a modifier governed specifically by a preposition.	nmod:prep (Katė ant kilimėlio)
:assmod	Associative Modifier	Common in Romanian/Baltic languages; shows nouns modifying other nouns.	nmod:assmod (Mano tėvo automobilis)
:poss	Possessive	Indicates ownership or a possessive relationship.	nmod:poss (Mano šuo, Jono kepurė)
:relcl	Relative Clause	Identifies a clause that modifies a noun phrase.	acl:relcl (Knyga, kurią perskaičiau)
:tmod	Temporal Modifier	A modifier specifically describing time or duration.	nmod:tmod (Išvykstu antradienį)
:prt	Particle	Used for phrasal verb particles.	compound:prt (Pasiduoti, išjungti)
:rcomp	Relative Complement	Used for complements of relative clauses (common in Dutch).	advcl:rcomp (Vyras, kuris išėjo)
:flat	Flat Modifier	Used for multi-word expressions that don't have a clear internal head.	flat:name (Prezidentas Obama)

Named Entity Recognition

NER (Named Entity Recognition) is a Natural Language Processing (NLP) task that automatically identifies and categorizes key information (entities) in a text into predefined classes. In spaCy, the statistical model "looks" at the context of a word to determine if it refers to a person, an organization, a monetary value, or a specific date. This is crucial for extracting structured data from unstructured text, such as finding all the company names mentioned in a news article or identifying the dates of events in a history book.

Comparison Note: GPE vs. LOC
Determining whether a place is a GPE or a LOC depends on its political nature:
GPE (Geopolitical Entity): If the location has a government, specific laws, or human-defined administrative borders, it is labeled as a GPE. Examples include Seoul, Germany, the United Kingdom, and California.
LOC (Location): If the place is a natural physical feature or a broad geographic region without a singular governing body, it is labeled as a LOC. Examples include the Alps, the Pacific Ocean, the Middle East, and Mount Everest.

NER Named Entity Recognition
Label	Meaning	Example
🌍 GPE	Geopolitical entity (countries, cities, states)	Lietuva, Vilnius, Prancūzija, Kalifornija
🏔️ LOC	Non-political location (mountains, rivers)	Ramusis vandenynas, Everesto kalnas, Alpės
🏢 FAC	Facility (buildings, airports, highways)	Golden Gate tiltas, Vilniaus oro uostas, Burdž Chalifa
👤 PERSON	People (real or fictional)	Elon Musk, Haris Poteris, Alanas Tiuringas
🚩 NORP	Nationalities, religious or political groups	Amerikietis, budistas, Demokratai, japonas
🏢 ORG	Organizations (companies, institutions)	Google, Jungtinės Tautos, Apple, FIFA
📅 DATE	Absolute or relative dates	Liepos 4 d., 2026 m., vakar, kitą savaitę
⌚ TIME	Times smaller than a day	9:30 val., saulėlydis, dešimt minučių
🎊 EVENT	Named events (wars, festivals)	Antrasis pasaulinis karas, Coachella, Olimpinės žaidynės
💰 MONEY	Monetary values, including unit	$100, 5 milijonai eurų, £50
‱ PERCENT	Percentage, including "%"	20 %, aštuoniasdešimt procentų, 0,5 %
⚖️ QUANTITY	Measurements (weight, distance)	5 km, 50 kg, 30 kvadratinių metrų
🔢 ORDINAL	"First", "second", etc.	pirmas, antras, devintas
🔢 CARDINAL	Numbers not classified elsewhere	10, tūkstantis, trys
📦 PRODUCT	Objects, vehicles, foods, etc. (not services)	iPhone, Tesla Model S, Coca-Cola
🎨 WORK_OF_ART	Titles of books, songs, etc.	Mona Liza, Bohemian Rhapsody, Hamletas
📜 LAW	Named legal documents	Konstitucija, Versalio sutartis
🗣️ LANGUAGE	Named languages	Lietuvių kalba, Python, mandarinų kalba

NLP pavyzdys (NLP Example)

Jei apdorojame frazę „Google yra įsikūrusi Kalifornijoje“ (Google is based in California), analizės lygmenys atrodo taip:

Lema (Lemma): "Google", "būti", "įsikurti", "Kalifornija"
UPOS: "PROPN(Tikrinis daiktavardis)", "AUX(Pagalbinis veiksmažodis)", "VERB(Veiksmažodis)", "ADP(Prielinksnis)", "PROPN(Tikrinis daiktavardis)"
XPOS (ALKSNIS): "dktv.tikr.vyr.vns.V.", "vksm.asm.tiesiog.es.treč.", "vksm.dlv.neveik.būt-k.vyr.vns.V.", "prl.kilm.", "dktv.tikr.mot.vns.Vt."
DEP: „Google“ yra vardinis paksubjektis (nsubj:pass) pasyvios konstrukcijos veiksmažodžiui „įsikūrusi“, kuris yra sakinio šaknis (Root). „yra“ yra pagalbinis veiksmažodis (aux:pass). „Kalifornijoje“ yra vietos aplinkybė (obl).
NER: „Google“ yra 🏢 ORG (Organizacija), „Kalifornija“ yra 🌍 GPE (Geopolitinis vienetas).

Universal POS, Detailed POS, NER, DEP

UPOS (Universal POS)

XPOS (Detailed POS)

Dependency

Named Entity Recognition

NLP pavyzdys (NLP Example)

Part-of-Speech for Main Languages