English 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 English UPOS tagging now.

UPOS Universal Part-of-Speech
Group	Tag	Meaning	Example
Open Class	ADJ	Adjective	big, old, green, incomprehensible, first
	ADV	Adverb	very, tomorrow, down, where, there
	INTJ	Interjection	psst, ouch, bravo, hello
	NOUN	Noun (common)	girl, cat, tree, air, beauty
	PROPN	Proper Noun	Mary, John, London, NATO, HBO
	VERB	Verb	run, runs, running, eat, ate, eaten
Closed Class	ADP	Adposition	in, to, during
	AUX	Auxiliary	is, has (done), will (do), should (do)
	CONJ	Conjunction	and, or, but (legacy tag)
	CCONJ	Coordinating Conjunction	and, or, but
	SCONJ	Subordinating Conjunction	if, while, that
	DET	Determiner	a, an, the
	NUM	Numeral	1, 2017, one, seventy-seven, MMXIV
	PART	Particle	's, not
	PRON	Pronoun	I, you, he, she, myself, themselves, somebody
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.

While UPOS might simply label a word as a "VERB," English XPOS—typically based on the Penn Treebank (PTB) tagset—distinguishes between six different verb forms, including the base form (VB), past tense (VBD), and 3rd person singular present (VBZ). For English learners and NLP developers, this detail is critical: it allows you to pinpoint the exact grammatical function of a word, such as whether "reading" is acting as a gerund (VBG) or part of a noun phrase. By capturing these nuances of tense, number, and case, XPOS provides the precise roadmap needed to master English syntax and sophisticated sentence construction.

Try our English XPOS tagging now.

English xpos Tags (Penn Treebank)
Category	Tag	Meaning	Example
Nouns	NN	Noun, singular or mass	dog, water
	NNS	Noun, plural	dogs, cats
	NNP	Proper noun, singular	London, Alice
	NNPS	Proper noun, plural	Americans, Olympics
	FW	Foreign word	de facto, persona non grata
Verbs & Modals	VB	Verb, base form	eat, go
	VBD	Verb, past tense	ate, went
	VBG	Verb, gerund or present participle	eating, going
	VBN	Verb, past participle	eaten, gone
	VBP	Verb, non-3rd person singular present	eat (I eat)
	VBZ	Verb, 3rd person singular present	eats (He eats)
	MD	Modal	could, will, should
Adjectives	JJ	Adjective	happy, green
	JJR	Adjective, comparative	happier, greener
	JJS	Adjective, superlative	happiest, greenest
Pronouns	PRP	Personal pronoun	I, he, she, it
	PRP$	Possessive pronoun	my, his, her
	WP	Wh-pronoun	who, what
	WP$	Possessive wh-pronoun	whose
Adverbs	RB	Adverb	quickly, very
	RBR	Adverb, comparative	faster
	RBS	Adverb, superlative	fastest
	WRB	Wh-adverb	where, when
Determiners & Conjunctions	DT	Determiner	the, a
	WDT	Wh-determiner	which, that
	PDT	Predeterminer	all (the), both (the)
	CC	Coordinating conjunction	and, but
	IN	Preposition or subordinating conjunction	in, of, that
Particles & Others	CD	Cardinal number	one, 5
	POS	Possessive ending	's
	RP	Particle	up (give up), off
	TO	to	to (go)
	EX	Existential there	there (is)
	UH	Interjection	oops, hello, wow
	SYM	Symbol	+, %, &
	LS	List item marker	1), a.

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	Elon eats.
	csubj	Clausal subject	What he did was wrong.
	obj	Direct object	I see the moon.
	iobj	Indirect object	She gave me a gift.
	ccomp	Clausal complement (finite)	He said he was tired.
	xcomp	Open clausal complement	I want to go.
Non-Core Dependents	obl	Oblique nominal	He sat on the chair.
	vocative	Vocative	John, come here!
	expl	Expletive	There is a cat.
	dislocated	Dislocated element	That man, I know him.
	advcl	Adverbial clause modifier	I left after he arrived.
	advmod	Adverbial modifier	Run fast.
	discourse	Discourse element	Well, I'm not sure.
	aux	Auxiliary	I can see.
	cop	Copula	She is happy.
	mark	Subordinating marker	I know that you know.
Nominal Dependents	nmod	Nominal modifier	The car's door.
	appos	Appositional modifier	Sam, my friend.
	nummod	Numeric modifier	Seven days.
	acl	Adjectival clause	The plan to win.
	amod	Adjectival modifier	The blue sky.
	det	Determiner	The end.
	case	Case marking	The king of France.
	fixed	Fixed multiword expression	In spite of that.
	flat	Flat multiword name	New York City.
	compound	Compound noun	Phone booth.
	list	List element	Phone, keys, wallet.
Coordination	conj	Conjunct	Bread and butter.
Coordination	cc	Coordinating conjunction	Bread and butter.
Special Labels	aux:pass	Passive auxiliary	It was stolen.
	punct	Punctuation	Hello!
	dep	Unspecified dependency	(Used for unknown links)
	ROOT	Root of the sentence	I ate lunch.

Common Dependency Attachments (Sub-labels)
Attachment	Full Name	Explanation	Example
:pass	Passive	Indicates a relationship in a passive voice construction.	nsubj:pass (The window was broken)
:nn	Noun Compound	Indicates that a noun is modifying another noun in a compound structure.	compound:nn (Phone charger)
:prep	Prepositional	Refines a modifier governed specifically by a preposition.	nmod:prep (The cat on the mat)
:assmod	Associative Modifier	Common in Romanian/Baltic languages; shows nouns modifying other nouns.	nmod:assmod (The car of my father)
:poss	Possessive	Indicates ownership or a possessive relationship.	nmod:poss (My dog, John's hat)
:relcl	Relative Clause	Identifies a clause that modifies a noun phrase.	acl:relcl (The book that I read)
:tmod	Temporal Modifier	A modifier specifically describing time or duration.	nmod:tmod (I'm leaving Tuesday)
:prt	Particle	Used for phrasal verb particles.	compound:prt (Give up, shut down)
:rcomp	Relative Complement	Used for complements of relative clauses (common in Dutch).	advcl:rcomp (The man who left)
:flat	Flat Modifier	Used for multi-word expressions that don't have a clear internal head.	flat:name (President 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)	USA, New York, France, California
🏔️ LOC	Non-political location (mountains, rivers)	Pacific Ocean, Mount Everest, The Alps
🏢 FAC	Facility (buildings, airports, highways)	Golden Gate Bridge, JFK Airport, Burj Khalifa
👤 PERSON	People (real or fictional)	Elon Musk, Harry Potter, Alan Turing
🚩 NORP	Nationalities, religious or political groups	American, Buddhist, Democrats, Japanese
🏢 ORG	Organizations (companies, institutions)	Google, United Nations, Apple, FIFA
📅 DATE	Absolute or relative dates	July 4th, 2026, yesterday, next week
⌚ TIME	Times smaller than a day	9:30 AM, sunset, ten minutes
🎊 EVENT	Named events (wars, festivals)	World War II, Coachella, Olympic Games
💰 MONEY	Monetary values, including unit	$100, 5 million Euro, £50
‱ PERCENT	Percentage, including "%"	20%, eighty percent, 0.5%
⚖️ QUANTITY	Measurements (weight, distance)	5km, 100lbs, 30 square meters
🔢 ORDINAL	"First", "second", etc.	first, 2nd, ninth
🔢 CARDINAL	Numbers not classified elsewhere	10, one thousand, three
📦 PRODUCT	Objects, vehicles, foods, etc. (not services)	iPhone, Tesla Model S, Coca-Cola
🎨 WORK_OF_ART	Titles of books, songs, etc.	Mona Lisa, Bohemian Rhapsody, Hamlet
📜 LAW	Named legal documents	The Constitution, Treaty of Versailles
🗣️ LANGUAGE	Named languages	English, Python, Mandarin

Universal POS, Detailed POS, NER, DEP

UPOS (Universal POS)

XPOS (Detailed POS)

Dependency

Named Entity Recognition

NLP Example

Part-of-Speech for Main Languages