Universal POS, Detailed POS, 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 Swedish UPOS tagging now.

UPOS Universal Part-of-Speech
Group Tag Meaning Example
Open Class ADJ Adjective stor, gammal, grön, obegriplig, första
ADV Adverb mycket, imorgon, ner, var, där
INTJ Interjection psst, aj, bravo, hej
NOUN Noun (common) flicka, katt, träd, luft, skönhet
PROPN Proper Noun Maria, Johan, London, NATO, HBO
VERB Verb springa, springer, springande, äta, åt, ätit
Closed Class ADP Adposition i, till, under
AUX Auxiliary är, har (gjort), ska, borde
CONJ Conjunction och, eller, men (legacy-tagg)
CCONJ Coordinating Conjunction och, eller, men
SCONJ Subordinating Conjunction om, medan, att
DET Determiner en, ett, den, det
NUM Numeral 1, 2017, en, sjuttiosju, MMXIV
PART Particle s, inte
PRON Pronoun jag, du, han, hon, mig själv, sig själva, någon
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.

Swedish XPOS tags following the SUC (Stockholm-Umeå Corpus) tagset, use a hierarchical pipe-separated structure. The primary tag (e.g., DT for Determiner or PP for Preposition) identifies the word's grammatical function, while the subsequent segments define its morphological properties. For example, DT|UTR|SIN|IND describes an indefinite, singular, common-gender determiner like "en." Proper nouns (PM) and punctuation (MAD, MID, PAD) are given their own top-level labels to ensure syntactic dependency parsing remains precise.

Try our Swedish XPOS tagging now.

Swedish xpos morphological detail
Category Abbreviation Swedish Term English Meaning Example
Core & Functional POS NN Substantiv Common Noun bil (car)
PM Eget namn (Proprium) Proper Noun Sverige, Maria
DT Determinerare Determiner en, ett, denna
PP Preposition Preposition i, på, med
PN Pronomen Pronoun jag, den
PS Possessivt pronomen Possessive Pronoun min, hans
VB Verb Verb springa
Numbers & Adverbs RG Grundtal Cardinal Number tre, 10
RO Ordningstal Ordinal Number tredje, 3:e
AB Adverb Adverb inte, ofta
HA Frågande adverb Interrogative Adverb när, var, hur
Punctuation MAD Meningavslutande Major Delimiter (End of sentence) . ! ?
MID Meninginternt Minor Delimiter (Internal) , ; :
PAD Parentetiskt Pair Delimiter " ( [
Morphology: Gender & Number UTR Utrum Common Gender (en) -
NEU Neutrum Neuter Gender (ett) -
MAS Maskulinum Masculine -
SIN Singular Singular -
PLU Plural Plural -
Morphology: Case & Form IND Obestämd Indefinite -
DEF Bestämd Definite -
NOM Nominativ Nominative -
GEN Genitiv Genitive -s
Verb & Adjective Specifics PRS Presens Present Tense läser
PRT Preteritum Past Tense läste
SUP Supinum Supine (with 'have') läst
INF Infinitiv Infinitive läsa
AKT Aktiv Active Voice -
SFO S-form Passive / S-form läsas, läses
POS Positiv Positive Degree fin

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 äter.
csubj Clausal subject Vad han gjorde var fel.
obj Direct object Jag ser månen.
iobj Indirect object Hon gav mig en present.
ccomp Clausal complement (finite) Han sa att han var trött.
xcomp Open clausal complement Jag vill .
Non-Core Dependents obl Oblique nominal Han satt på stolen.
vocative Vocative Johan, kom hit!
expl Expletive Det finns en katt.
dislocated Dislocated element Den mannen känner jag.
advcl Adverbial clause modifier Jag gick efter att han anlände.
advmod Adverbial modifier Spring fort.
discourse Discourse element Tja, jag är inte säker.
aux Auxiliary Jag kan se.
cop Copula Hon är glad.
mark Subordinating marker Jag vet att du vet.
Nominal Dependents nmod Nominal modifier Bilens dörr.
appos Appositional modifier Sam, min vän.
nummod Numeric modifier Sju dagar.
acl Adjectival clause Planen att vinna.
amod Adjectival modifier Den blå himlen.
det Determiner Slutet.
case Case marking Kungen av Frankrike.
fixed Fixed multiword expression Trots det.
flat Flat multiword name Staden New York.
compound Compound noun Telefonkiosk.
list List element Telefon, nycklar, plånbok.
Coordination conj Conjunct Bröd och smör.
cc Coordinating conjunction Bröd och smör.
Special Labels aux:pass Passive auxiliary Den blev stulen.
punct Punctuation Hej!
dep Unspecified dependency (Används för okända länkar)
ROOT Root of the sentence Jag åt lunch.

Common Dependency Attachments (Sub-labels)
Attachment Full Name Explanation Example
:pass Passive Indicates a relationship in a passive voice construction. nsubj:pass (Fönstret krossades)
:nn Noun Compound Indicates that a noun is modifying another noun in a compound structure. compound:nn (Mobilladdare)
:prep Prepositional Refines a modifier governed specifically by a preposition. nmod:prep (Katten mattan)
:assmod Associative Modifier Common in Romanian/Baltic languages; shows nouns modifying other nouns. nmod:assmod (Min fars bil)
:poss Possessive Indicates ownership or a possessive relationship. nmod:poss (Min hund, Johans hatt)
:relcl Relative Clause Identifies a clause that modifies a noun phrase. acl:relcl (Boken som jag läste)
:tmod Temporal Modifier A modifier specifically describing time or duration. nmod:tmod (Jag åker på tisdag)
:prt Particle Used for phrasal verb particles. compound:prt (Ge upp, stänga av)
:rcomp Relative Complement Used for complements of relative clauses (common in Dutch). advcl:rcomp (Mannen som gav sig av)
: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) Sverige, Stockholm, Frankrike, Kalifornien
🏔️ LOC Non-political location (mountains, rivers) Stilla havet, Mount Everest, Alperna
🏢 FAC Facility (buildings, airports, highways) Golden Gate-bron, Arlanda flygplats, Burj Khalifa
👤 PERSON People (real or fictional) Elon Musk, Harry Potter, Alan Turing
🚩 NORP Nationalities, religious or political groups Amerikan, buddhist, demokrater, japan
🏢 ORG Organizations (companies, institutions) Google, Förenta Nationerna, Apple, FIFA
📅 DATE Absolute or relative dates 4 juli, 2026, igår, nästa vecka
⌚ TIME Times smaller than a day 09:30, solnedgång, tio minuter
🎊 EVENT Named events (wars, festivals) Andra världskriget, Coachella, Olympiska spelen
💰 MONEY Monetary values, including unit $100, 5 miljoner euro, £50
‱ PERCENT Percentage, including "%" 20 %, åttio procent, 0,5 %
⚖️ QUANTITY Measurements (weight, distance) 5 km, 50 kg, 30 kvadratmeter
🔢 ORDINAL "First", "second", etc. första, andra, nionde
🔢 CARDINAL Numbers not classified elsewhere 10, tusen, tre
📦 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 Konstitutionen, Versaillesfreden
🗣️ LANGUAGE Named languages Svenska, Python, kinesiska (mandarin)

NLP-exempel (NLP Example)

Om vi bearbetar frasen "Google är baserat i Kalifornien" (Google is based in California) ser analysnivåerna ut så här:

Lemma: "Google", "vara", "basera", "i", "Kalifornien"
UPOS: "PROPN(Eget namn)", "AUX(Hjälpverb)", "VERB(Huvudverb)", "ADP(Preposition)", "PROPN(Eget namn)"
XPOS (SUC): "PM|NOM", "VB|PRS|AKT", "PC|PRF|UTR|SIN|IND|NOM", "PP", "PM|NOM"
DEP: "Google" är det nominala subjektet (nsubj:pass) för passivformen av verbet "baserat" som utgör meningens rot (Root). "är" är hjälpverbet (aux:pass). "Kalifornien" är en adverbial bestämning (obl) kopplad med prepositionen "i".
NER: "Google" är en 🏢 ORG (Organisation), "Kalifornien" är en 🌍 GPE (Geopolitisk enhet).

Part-of-Speech for Main Languages

Arabic - Catalan - Chinese - Classical Chinese - Croatian - Danish - Dutch - English - Filipino - Finnish - French - German - Greek - Hebrew - Hindi - Italian - Indonesian - Japanese - Korean - Latin - Lithuanian - Macedonian - Norwegian - Polish - Portuguese - Romanian - Russian - Slovenian - Sanskrit - Spanish - Swedish - Tamil - Thai - Ukrainian - Vietnamese

  • Home
  • Translators
  • Dictionaries
  • Grammars
  • Keyboards
  • Facebook

    © Stars21 - All Rights Reserved