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 Slovenian UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | velik, star, zelen, nerazumljiv, prvi |
| ADV | Adverb | zelo, jutri, navzdol, kje, tam | |
| INTJ | Interjection | pst, joj, bravo, živijo | |
| NOUN | Noun (common) | dekle, mačka, drevo, zrak, lepota | |
| PROPN | Proper Noun | Marija, Janez, London, NATO, HBO | |
| VERB | Verb | teči, teče, tekoč, jesti, jedel, pojeden | |
| Closed Class | ADP | Adposition | v, k, med |
| AUX | Auxiliary | je, je (naredil), bo, bi moral | |
| CONJ | Conjunction | in, ali, toda (stara oznaka) | |
| CCONJ | Coordinating Conjunction | in, ali, toda | |
| SCONJ | Subordinating Conjunction | če, medtem ko, da | |
| DET | Determiner | —, —, — | |
| NUM | Numeral | 1, 2017, ena, sedeminsedemdeset, MMXIV | |
| PART | Particle | —, ne | |
| PRON | Pronoun | jaz, ti, on, ona, jaz sam, oni sami, nekdo | |
| 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.
Slovenian XPOS tags follow a strictly positional logic. Each tag string (e.g., Ncmsn) acts as a compact code: N (Noun), c (common), m (masculine), s (singular), n (nominative). Unlike many other Slavic languages, Slovenian maintains the Dual number (represented by d) across nouns, adjectives, pronouns, and verbs. It also distinguishes between the Infinitive (n) and the Supine (u) mood.
| Category | Head Tag | Meaning / Sub-types | Example |
|---|---|---|---|
| Nouns (Samostalnik) | Nc | Common Noun (Občno ime) | knjiga (book), mačka (cat) |
| Np | Proper Noun (Lastno ime) | Slovenija, Marko, Drava | |
| Verbs (Glagol) | Vm | Main Verb (Glavni glagol) | delati (to work), grem (I go) |
| Va | Auxiliary Verb (Pomožni glagol) | sem (am), boš (will be) | |
| Adjectives (Pridevnik) | Agp | General Adjective, Positive degree | lep (beautiful), hiter (fast) |
| Agc | General Adjective, Comparative | lepši (more beautiful) | |
| Ags | General Adjective, Superlative | najlepši (most beautiful) | |
| Pronouns (Zaimki) | Pp | Personal Pronoun (Osebni) | jaz (I), midva (we two - dual) |
| Pd | Demonstrative Pronoun (Kazalni) | ta (this), tisti (that) | |
| Pi | Indefinite Pronoun (Nedoločni) | nekdo (someone), nekaj | |
| Ps | Possessive Pronoun (Svojilni) | moj (my), najin (our - dual) | |
| Adverb | Rg | General Adverb (Prislov) | hitro (quickly), doma (at home) |
| Preposition | S | Preposition (Predlog) + Case | v (in), na (on), pred (before) |
| Connectors | Cc | Coordinating Conjunction (Veznik) | in (and), ali (or), ampak |
| Cs | Subordinating Conjunction | da (that), ker (because), če (if) | |
| Particle | Q | Particle (Členek) | že (already), morda (maybe) |
| Numerals (Številnik) | Mc | Cardinal Numeral (Glavni) | ena (one), tisoč (thousand) |
| Mo | Ordinal Numeral (Vrstilni) | prvi (first), tretji (third) | |
| Miscellaneous | I | Interjection (Medmet) | oj!, joj!, hov! |
| Y | Abbreviation (Kratica) | itd. (etc.), d.o.o. | |
| Z | Punctuation (Ločilo) | ., ,, ?, ! | |
| X | Other / Foreign / Unknown | email, software |
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 je. |
| csubj | Clausal subject | To, kar je storil, je bilo napačno. | |
| obj | Direct object | Vidim luno. | |
| iobj | Indirect object | Dala mi je darilo. | |
| ccomp | Clausal complement (finite) | Rekel je, da je utrujen. | |
| xcomp | Open clausal complement | Želim iti. | |
| Non-Core Dependents | obl | Oblique nominal | Sedel je na stolu. |
| vocative | Vocative | Janez, pridi sem! | |
| expl | Expletive | Tam je mačka. | |
| dislocated | Dislocated element | Tistega moškega poznam. | |
| advcl | Adverbial clause modifier | Odšel sem, ko je prispel. | |
| advmod | Adverbial modifier | Teci hitro. | |
| discourse | Discourse element | No, nisem prepričan. | |
| aux | Auxiliary | Lahko vidim. | |
| cop | Copula | Ona je srečna. | |
| mark | Subordinating marker | Vem, da veš. | |
| Nominal Dependents | nmod | Nominal modifier | Vrata avtomobila. |
| appos | Appositional modifier | Sam, moj prijatelj. | |
| nummod | Numeric modifier | Sedem dni. | |
| acl | Adjectival clause | Načrt za zmago. | |
| amod | Adjectival modifier | Modro nebo. | |
| det | Determiner | Konec. | |
| case | Case marking | Kralj Francije. | |
| fixed | Fixed multiword expression | Kljub temu. | |
| flat | Flat multiword name | Mesto New York. | |
| compound | Compound noun | Telefonska govorilnica. | |
| list | List element | Telefon, ključi, denarnica. | |
| Coordination | conj | Conjunct | Kruh in maslo. |
| cc | Coordinating conjunction | Kruh in maslo. | |
| Special Labels | aux:pass | Passive auxiliary | Bilo je ukradeno. |
| punct | Punctuation | Živijo! | |
| dep | Unspecified dependency | (Uporablja se za neznane povezave) | |
| ROOT | Root of the sentence | Jedel sem kosilo. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Okno je bilo razbito) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Polnilnik za telefon) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Mačka na blazini) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Avto mojega očeta) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Moj pes, klobuk Janeza) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Knjiga, ki sem jo prebral) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Odhod v torek) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Odnehaj, izklopi) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Moški, ki je odšel) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Predsednik 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) | Slovenija, Ljubljana, Francija, Kalifornija |
| 🏔️ LOC | Non-political location (mountains, rivers) | Tihi ocean, Mount Everest, Alpe |
| 🏢 FAC | Facility (buildings, airports, highways) | Most Golden Gate, Letališče Jožeta Pučnika, Burdž Kalifa |
| 👤 PERSON | People (real or fictional) | Elon Musk, Harry Potter, Alan Turing |
| 🚩 NORP | Nationalities, religious or political groups | Američan, budist, demokrati, Japonec |
| 🏢 ORG | Organizations (companies, institutions) | Google, Združeni narodi, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | 4. julij, 2026, včeraj, naslednji teden |
| ⌚ TIME | Times smaller than a day | 9:30 zjutraj, sončni zahod, deset minut |
| 🎊 EVENT | Named events (wars, festivals) | Druga svetovna vojna, Coachella, Olimpijske igre |
| 💰 MONEY | Monetary values, including unit | $100, 5 milijonov evrov, £50 |
| ‱ PERCENT | Percentage, including "%" | 20 %, osemdeset odstotkov, 0,5 % |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5 km, 50 kg, 30 kvadratnih metrov |
| 🔢 ORDINAL | "First", "second", etc. | prvi, drugi, deveti |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, tisoč, tri |
| 📦 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, Hamlet |
| 📜 LAW | Named legal documents | Ustava, Versajska pogodba |
| 🗣️ LANGUAGE | Named languages | Slovenščina, Python, mandarinščina |
Če obdelamo stavek "Google ima sedež v Kaliforniji" (Google is based in California), so ravni analize videti takole:
Lema (Lemma): "Google", "imeti", "sedež", "v", "Kalifornija"
UPOS: "PROPN(Lastno ime)", "VERB(Glagol)", "NOUN(Samostalnik)", "ADP(Predlog)", "PROPN(Lastno ime)"
XPOS (MULTEXT-East): "Npmsn", "Vmpr3s-n", "Ncmsan", "Sl", "Npfsl"
DEP: "Google" je nominalni subjekt (nsubj) glagola "ima", ki je koren (Root) stavka. "sedež" je direktni objekt (obj), "Kaliforniji" pa je prislovno določilo (obl), povezano s predlogom "v".
NER: "Google" je 🏢 ORG (Organizacija), "Kalifornija" je 🌍 GPE (Geopolitična entiteta).
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
|
|||||