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 Romanian UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | mare, vechi, verde, de neînțeles, primul |
| ADV | Adverb | foarte, mâine, jos, unde, acolo | |
| INTJ | Interjection | pst, au, bravo, salut | |
| NOUN | Noun (common) | fată, pisică, copac, aer, frumusețe | |
| PROPN | Proper Noun | Maria, Ion, Londra, NATO, HBO | |
| VERB | Verb | a alerga, aleargă, alergând, a mânca, a mâncat, mâncat | |
| Closed Class | ADP | Adposition | în, la, în timpul |
| AUX | Auxiliary | este, a (făcut), va, ar trebui | |
| CONJ | Conjunction | și, sau, dar (tag vechi) | |
| CCONJ | Coordinating Conjunction | și, sau, dar | |
| SCONJ | Subordinating Conjunction | dacă, în timp ce, că | |
| DET | Determiner | un, o, cel, cea | |
| NUM | Numeral | 1, 2017, unu, șaptezeci și șapte, MMXIV | |
| PART | Particle | —, nu | |
| PRON | Pronoun | eu, tu, el, ea, eu însumi, ei înșiși, cineva | |
| 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.
In Romanian, the Definiteness feature (Position 6) is vital because the definite article is an "enclitic," meaning it attaches to the end of the noun or adjective. This distinguishes it from other Romance languages where articles are separate words. The Case system (Position 5) differentiates between "Direct" (Nominative/Accusative) and "Oblique" (Genitive/Dative).
Try our Romanian XPOS tagging now.
| Group | Position | Category | Label | Meaning |
|---|---|---|---|---|
| Core Category (Pos 1) | 1 | All | N | Noun (Substantiv) |
| V | Verb | |||
| A | Adjective | |||
| P | Pronoun | |||
| M | Numeral (Numeral) | |||
| T | Article (Articol) | |||
| Nominal (N/A/M/P) | 2 | Type | c / p | Common / Proper |
| 3 | Gender | m / f / n | Masculine / Feminine / Neuter | |
| 4 | Number | s / p | Singular / Plural | |
| 5 | Case | r | Direct (Rectus: Nom/Acc) | |
| o | Oblique (Obliquus: Gen/Dat) | |||
| v | Vocative | |||
| 6 | Definiteness | n | No definite article | |
| y | With definite article | |||
| Verbal (V) | 2 | Type | m / a / x | Main / Auxiliary / Modal |
| 3 | Mood | i | Indicative | |
| s | Subjunctive | |||
| m | Imperative | |||
| c | Conditional | |||
| 4 | Tense | p | Present | |
| i | Imperfect | |||
| s | Simple Perfect | |||
| 5 / 6 | Person / Num | 1, 2, 3 / s, p | 1st/2nd/3rd Person / Sing/Plural | |
| Lexical (M/P) | 2 | Type | c | Cardinal Numeral |
| o | Ordinal Numeral | |||
| p | Personal Pronoun | |||
| d | Demonstrative Pronoun | |||
| 3 | Person | 1, 2, 3 | For pronouns | |
| - | Possession | s / p | Possessor Number (for possessives) | |
| Special | - | Other | Y | Abbreviation |
| f | Foreign Word |
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 mănâncă. |
| csubj | Clausal subject | Ce a făcut a fost greșit. | |
| obj | Direct object | Văd luna. | |
| iobj | Indirect object | Ea mi-a dat un cadou. | |
| ccomp | Clausal complement (finite) | A spus că este obosit. | |
| xcomp | Open clausal complement | Vreau să merg. | |
| Non-Core Dependents | obl | Oblique nominal | S-a așezat pe scaun. |
| vocative | Vocative | Ioane, vino aici! | |
| expl | Expletive | Acolo este o pisică. | |
| dislocated | Dislocated element | Îl cunosc pe omul acela. | |
| advcl | Adverbial clause modifier | Am plecat după ce a sosit. | |
| advmod | Adverbial modifier | Fugi repede. | |
| discourse | Discourse element | Ei bine, nu sunt sigur. | |
| aux | Auxiliary | Pot vedea. | |
| cop | Copula | Ea este fericită. | |
| mark | Subordinating marker | Știu că știi. | |
| Nominal Dependents | nmod | Nominal modifier | Ușa mașinii. |
| appos | Appositional modifier | Sam, prietenul meu. | |
| nummod | Numeric modifier | Șapte zile. | |
| acl | Adjectival clause | Planul de a câștiga. | |
| amod | Adjectival modifier | Cerul albastru. | |
| det | Determiner | Sfârșitul. | |
| case | Case marking | Regele Franței. | |
| fixed | Fixed multiword expression | În ciuda acestui fapt. | |
| flat | Flat multiword name | Orașul New York. | |
| compound | Compound noun | Cabină telefonică. | |
| list | List element | Telefon, chei, portofel. | |
| Coordination | conj | Conjunct | Pâine și unt. |
| cc | Coordinating conjunction | Pâine și unt. | |
| Special Labels | aux:pass | Passive auxiliary | A fost furat. |
| punct | Punctuation | Salut! | |
| dep | Unspecified dependency | (Folosit pentru legături necunoscute) | |
| ROOT | Root of the sentence | Am mâncat prânzul. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Fereastra a fost spartă) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Încărcător de telefon) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Pisica pe covor) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Mașina tatălui meu) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Câinele meu, pălăria lui Ioan) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Cartea pe care am citit-o) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Plec marți) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Renunță, oprește) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Omul care a plecat) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Președintele 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) | România, București, Franța, California |
| 🏔️ LOC | Non-political location (mountains, rivers) | Oceanul Pacific, Muntele Everest, Alpii |
| 🏢 FAC | Facility (buildings, airports, highways) | Podul Golden Gate, Aeroportul Henri Coandă, Burj Khalifa |
| 👤 PERSON | People (real or fictional) | Elon Musk, Harry Potter, Alan Turing |
| 🚩 NORP | Nationalities, religious or political groups | American, budist, democrați, japonez |
| 🏢 ORG | Organizations (companies, institutions) | Google, Organizația Națiunilor Unite, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | 4 iulie, 2026, ieri, săptămâna viitoare |
| ⌚ TIME | Times smaller than a day | 9:30 dimineața, apus de soare, zece minute |
| 🎊 EVENT | Named events (wars, festivals) | Al Doilea Război Mondial, Coachella, Jocurile Olimpice |
| 💰 MONEY | Monetary values, including unit | $100, 5 milioane de euro, £50 |
| ‱ PERCENT | Percentage, including "%" | 20%, optzeci la sută, 0,5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5km, 50kg, 30 de metri pătrați |
| 🔢 ORDINAL | "First", "second", etc. | primul, al doilea, al nouălea |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, o mie, trei |
| 📦 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 | Constituția, Tratatul de la Versailles |
| 🗣️ LANGUAGE | Named languages | Română, Python, Mandarină |
Dacă procesăm fraza „Google are sediul în California” (Google is based in California), straturile de analiză arată astfel:
Lemă (Lemma): „Google”, „avea”, „sediu”, „în”, „California”
UPOS: „PROPN(Nume propriu)”, „VERB(Verb principal)”, „NOUN(Substantiv)”, „ADP(Prepoziție)”, „PROPN(Nume propriu)”
XPOS (MULTEXT-East): „Np”, „Vmip3s”, „Ncfry”, „Spsa”, „Np”
DEP: „Google” este subiectul nominal (nsubj) al verbului „are”, care este rădăcina propoziției (Root). „sediul” este obiectul direct (obj), iar „California” este un complement oblic (obl) conectat prin prepoziția „în”.
NER: „Google” este o 🏢 ORG (Organizație), iar „California” este o 🌍 GPE (Entitate geopolitică).
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
|
|||||