Korean 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 Korean UPOS tagging now.

UPOS Universal Part-of-Speech
Group	Tag	Meaning	Example
Open Class	ADJ	Adjective	큰, 오래된, 푸른, 이해불가인, 첫번째인
	ADV	Adverb	매우, 내일, 아래로, 어디, 저기
	INTJ	Interjection	쉿, 아야, 브라보, 안녕
	NOUN	Noun (common)	소녀, 고양이, 나무, 공기, 미
	PROPN	Proper Noun	메리, 존, 런던, 나토, HBO
	VERB	Verb	달리다, 달린다, 달리는 중인, 먹다, 먹었다, 먹힌
Closed Class	ADP	Adposition	안에, ~로, ~동안
	AUX	Auxiliary	이다, 했다, 할 것이다, 해야 한다
	CONJ	Conjunction	그리고, 또는, 하지만 (레거시 태그)
	CCONJ	Coordinating Conjunction	그리고, 또는, 하지만
	SCONJ	Subordinating Conjunction	만약, ~동안, 그것
	DET	Determiner	하나의, 그
	NUM	Numeral	1, 2017, 하나, 일흔일곱, MMXIV
	PART	Particle	의, 아니다
	PRON	Pronoun	나, 너, 그, 그녀, 나 자신, 그들 자신, 누군가
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.

The Korean XPOS system follows a highly modular logic designed for an agglutinative language. The KAIST-style tags you encountered differentiate between types of common nouns (e.g., action nouns vs. non-action nouns) and provide specific codes for various types of particles (Josa). This allows developers to distinguish between a noun used as a simple subject and a noun that can function as a verb stem when combined with -하다.

Try our Korean XPOS tagging now.

Complete Korean xpos morphological detail (KAIST Tagset)
Category	Abbreviation	Korean Term	English Meaning	Example
Nouns (체언)	ncn	보통 명사	Common Noun (Non-predicative)	하늘 (sky), 집
	ncpa	동작 명사	Action Noun (Predicative)	공부 (study), 운동
	ncps	상태 명사	State Noun	행복 (happiness)
	nq	고유 명사	Proper Noun	한국, 이순신
	nbn	일반 의존 명사	General Bound Noun	것, 데, 바
	nbu	단위 의존 명사	Unit Bound Noun	개, 병, 마리
	nnc	수사	Cardinal Numeral	하나, 둘, 일, 이
	nno	서수사	Ordinal Numeral	첫째, 둘째
Pronouns	npp	인칭 대명사	Personal Pronoun	나, 너, 그
	npd	지시 대명사	Demonstrative Pronoun	이것, 저것, 거기
	npr	의문 대명사	Interrogative Pronoun	누구, 무엇, 어디
Predicates (용언)	pvg	일반 동사	General Verb Stem	가(다), 먹(다)
	paa	형용사	Adjective Stem	예쁘(다), 작(다)
	px	보조 용언	Auxiliary Verb/Adj	(하지) 않다, (먹어) 보다
	vcp	긍정 지정사	Positive Copula	이(다)
	vcn	부정 지정사	Negative Copula	아니(다)
Particles (조사)	jcs	주격 조사	Subject Case Particle	이, 가, 께서
	jco	목적격 조사	Object Case Particle	을, 를
	jca	부사격 조사	Adverbial Case Particle	에, 에서, 로, 와
	jcc	보격 조사	Complement Case Particle	이, 가 (with 아니다)
	jcg	관형격 조사	Genitive Case Particle	의
	jcv	호격 조사	Vocative Particle	아, 야, 이여
	jcm	접속 조사	Conjunctive Particle	와, 과, 랑
	jxt	화제 보조사	Topical Particle	은, 는
	jxf	초점 보조사	Focus Particle	도, 만, 조차
	jp	서술격 조사	Predictive Particle (Postposition)	이다
Endings (어미)	ep	선어말 어미	Pre-final Ending	-었-, -시-, -겠-
	ef	종결 어미	Final Ending	-다, -요, -느냐
	ecc	대등 연결 어미	Coordinating Ending	-고, -며, -거나
	ecs	종속 연결 어미	Subordinating Ending	-면, -니까, -려고
	ecx	보조적 연결 어미	Auxiliary Ending	-아, -어, -게, -지
	etn	명사형 전성 어미	Nominalizing Ending	-기, -음
	etm	관형사형 전성 어미	Adnominalizing Ending	-는, -은, -을, -던
Modifiers & Affixes	mm	관형사	Determiner	이, 그, 저, 새
	mag	일반 부사	General Adverb	매우, 빨리, 전혀
	xp	접두사	Prefix	맨-, 햇-
	xs	접미사	Suffix	-들, -보, -님
	ic	감탄사	Interjection	아, 에고, 야
	sl / sn	외국어 / 숫자	Foreign Word / Number	Apple / 123

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	머스크가 먹는다.
	csubj	Clausal subject	그가 한 일은 잘못되었다.
	obj	Direct object	나는 달을 본다.
	iobj	Indirect object	그녀는 나에게 선물을 주었다.
	ccomp	Clausal complement (finite)	그는 피곤하다고 말했다.
	xcomp	Open clausal complement	나는 가고 싶다.
Non-Core Dependents	obl	Oblique nominal	그는 의자에 앉았다.
	vocative	Vocative	철수야, 이리 와!
	expl	Expletive	고양이 한 마리가 있다.
	dislocated	Dislocated element	그 남자, 나는 그를 안다.
	advcl	Adverbial clause modifier	나는 그가 도착한 후에 떠났다.
	advmod	Adverbial modifier	빨리 달려라.
	discourse	Discourse element	글쎄, 잘 모르겠다.
	aux	Auxiliary	나는 볼 수 있다.
	cop	Copula	그녀는 행복하다.
	mark	Subordinating marker	나는 네가 알고 있다는 것을 안다.
Nominal Dependents	nmod	Nominal modifier	그 차의 문.
	appos	Appositional modifier	내 친구 샘.
	nummod	Numeric modifier	칠 일.
	acl	Adjectival clause	이길 계획.
	amod	Adjectival modifier	푸른 하늘.
	det	Determiner	그 끝.
	case	Case marking	프랑스의 왕.
	fixed	Fixed multiword expression	그것에도 불구하고.
	flat	Flat multiword name	서울시.
	compound	Compound noun	공중전화박스.
	list	List element	전화기, 열쇠, 지갑.
Coordination	conj	Conjunct	빵과 버터.
Coordination	cc	Coordinating conjunction	빵과 버터.
Special Labels	aux:pass	Passive auxiliary	그것은 도난당했다.
	punct	Punctuation	안녕!
	dep	Unspecified dependency	(알 수 없는 링크에 사용됨)
	ROOT	Root of the sentence	나는 점심을 먹었다.

Common Dependency Attachments (Sub-labels)
Attachment	Full Name	Explanation	Example
:pass	Passive	Indicates a relationship in a passive voice construction.	nsubj:pass (그 창문이 깨졌다)
:nn	Noun Compound	Indicates that a noun is modifying another noun in a compound structure.	compound:nn (휴대폰 충전기)
:prep	Prepositional	Refines a modifier governed specifically by a preposition.	nmod:prep (매트 위의 고양이)
:assmod	Associative Modifier	Common in Romanian/Baltic languages; shows nouns modifying other nouns.	nmod:assmod (내 아버지의 차)
:poss	Possessive	Indicates ownership or a possessive relationship.	nmod:poss (내 개, 철수의 모자)
:relcl	Relative Clause	Identifies a clause that modifies a noun phrase.	acl:relcl (내가 읽은 책)
:tmod	Temporal Modifier	A modifier specifically describing time or duration.	nmod:tmod (나는 화요일에 떠난다)
:prt	Particle	Used for phrasal verb particles.	compound:prt (포기하다, 종료하다)
:rcomp	Relative Complement	Used for complements of relative clauses (common in Dutch).	advcl:rcomp (떠난 남자)
:flat	Flat Modifier	Used for multi-word expressions that don't have a clear internal head.	flat:name (오바마 대통령)

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)	한국, 서울, 프랑스, 캘리포니아
🏔️ LOC	Non-political location (mountains, rivers)	태평양, 에베레스트산, 알프스산맥
🏢 FAC	Facility (buildings, airports, highways)	광안대교, 인천국제공항, 부르즈 할리파
👤 PERSON	People (real or fictional)	홍길동, 해리 포터, 세종대왕
🚩 NORP	Nationalities, religious or political groups	한국인, 불교도, 민주당원, 일본인
🏢 ORG	Organizations (companies, institutions)	삼성, 유엔, 애플, FIFA
📅 DATE	Absolute or relative dates	7월 4일, 2026년, 어제, 다음 주
⌚ TIME	Times smaller than a day	오전 9시 30분, 일몰, 10분
🎊 EVENT	Named events (wars, festivals)	제2차 세계 대전, 코첼라, 올림픽
💰 MONEY	Monetary values, including unit	10,000원, 500만 유로, 50파운드
‱ PERCENT	Percentage, including "%"	20%, 80퍼센트, 0.5%
⚖️ QUANTITY	Measurements (weight, distance)	5km, 50kg, 30제곱미터
🔢 ORDINAL	"First", "second", etc.	첫 번째, 2위, 아홉 번째
🔢 CARDINAL	Numbers not classified elsewhere	10, 천, 셋
📦 PRODUCT	Objects, vehicles, foods, etc. (not services)	아이폰, 제네시스 G80, 코카콜라
🎨 WORK_OF_ART	Titles of books, songs, etc.	모나리자, 보헤미안 랩소디, 춘향전
📜 LAW	Named legal documents	대한민국 헌법, 베르사유 조약
🗣️ LANGUAGE	Named languages	한국어, 파이썬, 중국어

Universal POS, Detailed POS, NER, DEP

UPOS (Universal POS)

XPOS (Detailed POS)

Dependency

Named Entity Recognition

NLP 예시 (NLP Example)

Part-of-Speech for Main Languages