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 Dutch UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | groot, oud, groen, onbegrijpelijk, eerste |
| ADV | Adverb | erg, morgen, beneden, waar, daar | |
| INTJ | Interjection | sst, au, bravo, hallo | |
| NOUN | Noun (common) | meisje, kat, boom, lucht, schoonheid | |
| PROPN | Proper Noun | Maria, Johannes, Londen, NAVO, HBO | |
| VERB | Verb | rennen, rent, rennend, eten, at, gegeten | |
| Closed Class | ADP | Adposition | in, naar, tijdens |
| AUX | Auxiliary | is, heeft (gedaan), zal (doen), zou (moeten doen) | |
| CONJ | Conjunction | en, of, maar (legacy-tag) | |
| CCONJ | Coordinating Conjunction | en, of, maar | |
| SCONJ | Subordinating Conjunction | als, terwijl, dat | |
| DET | Determiner | een, de, het | |
| NUM | Numeral | 1, 2017, een, zevenenzeventig, MMXIV | |
| PART | Particle | 's (genitief), niet | |
| PRON | Pronoun | ik, jij, hij, zij, mezelf, zichzelf, iemand | |
| Other | PUNCT | Punctuation | ., (, ), ?, ] |
| SYM | Symbol | $, %, +, −, :), 🐻 | |
| X | Other / Foreign | sfpksdpsxmsa, ..., foreign words | |
| SPACE | Space | newlines, tabs, extra spaces |
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.
Dutch XPOS Anatomy: Dutch XPOS tags are based on the CGN (Corpus Gesproken Nederlands) tagset. They are composed of a Primary Tag (the word category) followed by Morphological Features (specific grammatical attributes) often enclosed in parentheses or separated by pipes.
Structure: Category | Type | Tense/Degree | Number/Gender
Example: WW(pv,tgw,ev)
• English: Verb (Finite form, Present tense, Singular)
• Dutch: Werkwoord (Persoonsvorm, Tegenwoordige tijd, Enkelvoud)
Try our Dutch XPOS tagging now.
| Category | Tag | Meaning | Dutch Term |
|---|---|---|---|
| Nouns | N | Noun (General) | Zelfstandig naamwoord |
| N(soort) | Common noun | Soortnaam | |
| N(eigen) | Proper noun | Eigennaam | |
| Verbs | WW | Verb (General) | Werkwoord |
| WW(pv) | Finite verb | Persoonsvorm | |
| WW(inf) | Infinitive | Infinitief | |
| WW(vd) | Past participle | Voltooid deelwoord | |
| WW(od) | Present participle | Onvoltooid deelwoord | |
| Modifiers | ADJ | Adjective | Bijvoeglijk naamwoord |
| BW | Adverb | Bijwoord | |
| Pronouns & Articles | VNW | Pronoun | Voornaamwoord |
| LID | Article / Determiner | Lidwoord | |
| Adpositions | VZ | Preposition / Adposition | Voorzetsel |
| VZ(init) | Preposition (initial) | Voorzetsel | |
| VZ(fin) | Postposition (final) | Achterzetsel | |
| Conjunctions | VG | Conjunction (General) | Voegwoord |
| VG(neven) | Coordinating conjunction | Nevenschikkend | |
| VG(onder) | Subordinating conjunction | Onderschikkend | |
| Numerals | TW | Numeral (General) | Telwoord |
| TW(hoofd) | Cardinal numeral | Hoofdtelwoord | |
| TW(rang) | Ordinal numeral | Rangtelwoord | |
| Special & Others | TSW | Interjection | Tussenwerpsel |
| SPEC(deeleigen) | Part of a proper name | Deeleigennaam | |
| SPEC(vreemd) | Foreign word | Vreemd | |
| SPEC(symb) | Symbol | Symbool | |
| SPEC(afgebr) | Truncated word | Afgebroken | |
| Punctuation | LET | Punctuation | Leesteken |
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.
| Category | Label | Meaning | Example (Token in bold) |
|---|---|---|---|
| Core Arguments | nsubj | Nominal subject | Elon eet. |
| csubj | Clausal subject | Wat hij deed was fout. | |
| obj | Direct object | Ik zie de maan. | |
| iobj | Indirect object | Ze gaf mij een cadeau. | |
| ccomp | Clausal complement (finite) | Hij zei dat hij moe was. | |
| xcomp | Open clausal complement | Ik wil gaan. | |
| Non-Core Dependents | obl | Oblique nominal | Hij zat op de stoel. |
| vocative | Vocative | Johannes, kom hier! | |
| expl | Expletive | Er is een kat. | |
| dislocated | Dislocated element | Die man, ik ken hem. | |
| advcl | Adverbial clause modifier | Ik vertrok nadat hij aankwam. | |
| advmod | Adverbial modifier | Ren snel. | |
| discourse | Discourse element | Nou, ik weet het niet zeker. | |
| aux | Auxiliary | Ik kan zien. | |
| cop | Copula | Ze is blij. | |
| mark | Subordinating marker | Ik weet dat je het weet. | |
| Nominal Dependents | nmod | Nominal modifier | De deur van de auto. |
| appos | Appositional modifier | Sam, mijn vriend. | |
| nummod | Numeric modifier | Zeven dagen. | |
| acl | Adjectival clause | Het plan om te winnen. | |
| amod | Adjectival modifier | De blauwe lucht. | |
| det | Determiner | Het einde. | |
| case | Case marking | De koning van Frankrijk. | |
| fixed | Fixed multiword expression | Ondanks dat. | |
| flat | Flat multiword name | De stad Amsterdam. | |
| compound | Compound noun | Telefooncel. | |
| list | List element | Telefoon, sleutels, portemonnee. | |
| Coordination | conj | Conjunct | Brood en boter. |
| cc | Coordinating conjunction | Brood en boter. | |
| Special Labels | aux:pass | Passive auxiliary | Het werd gestolen. |
| punct | Punctuation | Hallo! | |
| dep | Unspecified dependency | (Gebruikt voor onbekende verbindingen) | |
| ROOT | Root of the sentence | Ik at de lunch. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Het raam was gebroken) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Telefoonoplader) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (De kat op de mat) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (De auto van mijn vader) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Mijn hond, Johannes' hoed) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Het boek dat ik las) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Ik vertrek dinsdag) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Geef op, sluit af) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (De man die vertrok) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (President Obama) |
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.
| Label | Meaning | Example |
|---|---|---|
| 🌍 GPE | Geopolitical entity (countries, cities, states) | Nederland, Amsterdam, Frankrijk, Californië |
| 🏔️ LOC | Non-political location (mountains, rivers) | Stille Oceaan, Mount Everest, De Alpen |
| 🏢 FAC | Facility (buildings, airports, highways) | Erasmusbrug, Schiphol, Burj Khalifa |
| 👤 PERSON | People (real or fictional) | Willem-Alexander, Harry Potter, Alan Turing |
| 🚩 NORP | Nationalities, religious or political groups | Nederlander, boeddhist, democraten, Japanner |
| 🏢 ORG | Organizations (companies, institutions) | Google, Verenigde Naties, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | 4 juli, 2026, gisteren, volgende week |
| ⌚ TIME | Times smaller than a day | 9:30 uur, zonsondergang, tien minuten |
| 🎊 EVENT | Named events (wars, festivals) | Tweede Wereldoorlog, Pinkpop, Olympische Spelen |
| 💰 MONEY | Monetary values, including unit | $100, 5 miljoen euro, £50 |
| ‱ PERCENT | Percentage, including "%" | 20%, tachtig procent, 0,5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5 km, 50 kg, 30 vierkante meter |
| 🔢 ORDINAL | "First", "second", etc. | eerste, 2e, negende |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, duizend, drie |
| 📦 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 | De Grondwet, Verdrag van Versailles |
| 🗣️ LANGUAGE | Named languages | Nederlands, Python, Mandarijn |
Als we de zin „Google is gevestigd in Amsterdam“ (Google is based in Amsterdam) verwerken, zien de lagen er als volgt uit:
Lemma (Llemma): "Google", "zijn", "gevestigd", "in", "Amsterdam"
UPOS (Universele woordsoorttags): "PROPN(Eigennaam)", "AUX(Hulpwerkwoord)", "VERB(Hoofdwerkwoord)", "ADP(Voorzetsel)", "PROPN(Eigennaam)"
XPOS (Specifieke CGN-woordsoorttags): "N(eigen,ev,neut)", "WW(pv,tgw,ev)", "WW(vd,vrij,zonder)", "VZ(init)", "N(eigen,ev,neut)"
DEP (Syntactische afhankelijkheden): „Google“ is het nsubj:pass (passief nominal subject) van de passieve constructie. „is“ is het aux:pass (passief hulpwerkwoord). „gevestigd“ is de Root (hoofdwerkwoord/sentence root). „Amsterdam“ is het obl (adverbiale bepaling) verbonden door het voorzetsel „in“.
NER (Herkenning van benoemde entiteiten): „Google“ is een 🏢 ORG (Organisatie), en „Amsterdam“ is een 🌍 GPE (Geopolitieke entiteit).
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
|
|
|
© Stars21 - All Rights Reserved
|
|||||