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 Italian UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | grande, vecchio, verde, incomprensibile, primo |
| ADV | Adverb | molto, domani, giù, dove, lì | |
| INTJ | Interjection | pst, ahi, bravo, ciao | |
| NOUN | Noun (common) | ragazza, gatto, albero, aria, bellezza | |
| PROPN | Proper Noun | Maria, Giovanni, Londra, NATO, HBO | |
| VERB | Verb | correre, corre, correndo, mangiare, mangiò, mangiato | |
| Closed Class | ADP | Adposition | in, a, durante |
| AUX | Auxiliary | è, ha (fatto), farà, dovrebbe | |
| CONJ | Conjunction | e, o, ma (tag legacy) | |
| CCONJ | Coordinating Conjunction | e, o, ma | |
| SCONJ | Subordinating Conjunction | se, mentre, che | |
| DET | Determiner | un, una, il, la | |
| NUM | Numeral | 1, 2017, uno, settantasette, MMXIV | |
| PART | Particle | —, non | |
| PRON | Pronoun | io, tu, lui, lei, me stesso, se stessi, qualcuno | |
| 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.
Italian XPOS tags follow the ISDT standard. While Italian is a highly inflected Romance language, the XPOS labels are relatively concise. The complexity is often handled by articulated forms; for example, E_RD indicates a preposition (E) fused with a definite article (RD). Unlike the Slavic systems that use a single long string, Italian morphology for gender and number is typically stored in separate attributes, while the XPOS identifies the specific functional subtype of the word.
Try our Italian XPOS tagging now.
| Category | Tag | Meaning | Example |
|---|---|---|---|
| Nouns | S | Common Noun (Sostantivo) | casa, libro, gatto |
| SP | Proper Noun (Nome proprio) | Italia, Mario, Roma | |
| Verbs | V | Main Verb (Verbo principale) | mangia, corre, vede |
| VA | Auxiliary Verb (Avere / Essere) | ha (fatto), è (andato) | |
| VM | Modal Verb (Dovere, Potere, Volere) | può, deve, vuole | |
| Modifiers | A | Adjective | bello, grande, veloce |
| AP | Possessive Adjective | mio, tuo, suo | |
| B | Adverb | bene, molto, ieri | |
| Pronouns | PP | Personal Pronoun | io, tu, noi |
| PC | Clitic Pronoun (Complement) | lo, la, mi, ti | |
| PD | Demonstrative Pronoun | questo, quello | |
| PI | Indefinite Pronoun | qualcuno, nessuno | |
| PR | Relative Pronoun | che, cui, il quale | |
| PQ | Interrogative Pronoun | chi?, cosa? | |
| RI | Reflexive Clitic | si, ci, vi | |
| Adpositions & Articles | RD | Definite Article | il, lo, la, i, gli, le |
| RI | Indefinite Article | un, uno, una | |
| E | Simple Preposition | di, a, da, in, con, su, per, tra, fra | |
| E_RD | Articulated Preposition | del, nella, sui, dagli | |
| Others | CC | Coordinating Conjunction | e, o, ma |
| CS | Subordinating Conjunction | perché, se, mentre | |
| I | Interjection | ah!, ehi!, bravo! | |
| N | Numeral | due, cento, 1990 | |
| SYM | Symbol | $, %, + | |
| X | Foreign word / Other | marketing, online | |
| Y | Abbreviation | ecc., prof. | |
| Punctuation | FF | Generic Punctuation / Hyphen | -, --, ... |
| FC | Comma | , | |
| FS | Sentence End Punctuation | ., !, ? | |
| FB | Brackets | (, ), [, ] |
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 mangia. |
| csubj | Clausal subject | Ciò che ha fatto era sbagliato. | |
| obj | Direct object | Vedo la luna. | |
| iobj | Indirect object | Lei mi ha dato un regalo. | |
| ccomp | Clausal complement (finite) | Ha detto che era stanco. | |
| xcomp | Open clausal complement | Voglio andare. | |
| Non-Core Dependents | obl | Oblique nominal | Si è seduto sulla sedia. |
| vocative | Vocative | Giovanni, vieni qui! | |
| expl | Expletive | C'è un gatto. | |
| dislocated | Dislocated element | Conosco quell'uomo. | |
| advcl | Adverbial clause modifier | Sono partito dopo che è arrivato. | |
| advmod | Adverbial modifier | Corri velocemente. | |
| discourse | Discourse element | Beh, non sono sicuro. | |
| aux | Auxiliary | Posso vedere. | |
| cop | Copula | Lei è felice. | |
| mark | Subordinating marker | So che lo sai. | |
| Nominal Dependents | nmod | Nominal modifier | La portiera della macchina. |
| appos | Appositional modifier | Sam, il mio amico. | |
| nummod | Numeric modifier | Sette giorni. | |
| acl | Adjectival clause | Il piano per vincere. | |
| amod | Adjectival modifier | Il cielo blu. | |
| det | Determiner | La fine. | |
| case | Case marking | Il re di Francia. | |
| fixed | Fixed multiword expression | Nonostante ciò. | |
| flat | Flat multiword name | La città di New York. | |
| compound | Compound noun | Cabina telefonica. | |
| list | List element | Telefono, chiavi, portafoglio. | |
| Coordination | conj | Conjunct | Pane e burro. |
| cc | Coordinating conjunction | Pane e burro. | |
| Special Labels | aux:pass | Passive auxiliary | È stato rubato. |
| punct | Punctuation | Ciao! | |
| dep | Unspecified dependency | (Usato per collegamenti sconosciuti) | |
| ROOT | Root of the sentence | Ho pranzato. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (La finestra è stata rotta) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Caricatore del telefono) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Il gatto sul tappeto) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (La macchina di mio padre) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Il mio cane, il cappello di Giovanni) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Il libro che ho letto) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Parto martedì) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Arrendersi, spegnere) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (L'uomo che se n'è andato) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Il presidente 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) | Italia, Roma, Francia, California |
| 🏔️ LOC | Non-political location (mountains, rivers) | Oceano Pacifico, Monte Everest, Le Alpi |
| 🏢 FAC | Facility (buildings, airports, highways) | Ponte del Golden Gate, Aeroporto Leonardo da Vinci, Burj Khalifa |
| 👤 PERSON | People (real or fictional) | Elon Musk, Harry Potter, Alan Turing |
| 🚩 NORP | Nationalities, religious or political groups | Americano, Buddista, Democratici, Giapponese |
| 🏢 ORG | Organizations (companies, institutions) | Google, Nazioni Unite, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | 4 luglio, 2026, ieri, la prossima settimana |
| ⌚ TIME | Times smaller than a day | 9:30, tramonto, dieci minuti |
| 🎊 EVENT | Named events (wars, festivals) | Seconda guerra mondiale, Coachella, Giochi Olimpici |
| 💰 MONEY | Monetary values, including unit | $100, 5 milioni di Euro, £50 |
| ‱ PERCENT | Percentage, including "%" | 20%, ottanta percento, 0,5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5km, 50kg, 30 metri quadrati |
| 🔢 ORDINAL | "First", "second", etc. | primo, secondo, nono |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, mille, tre |
| 📦 PRODUCT | Objects, vehicles, foods, etc. (not services) | iPhone, Tesla Model S, Coca-Cola |
| 🎨 WORK_OF_ART | Titles of books, songs, etc. | Monna Lisa, Bohemian Rhapsody, Amleto |
| 📜 LAW | Named legal documents | La Costituzione, Trattato di Versailles |
| 🗣️ LANGUAGE | Named languages | Italiano, Python, Mandarino |
Se elaboriamo la frase "Google ha sede in California" (Google is based in California), i livelli di analisi appaiono così:
Lemma: "Google", "avere", "sede", "in", "California"
UPOS: "PROPN(Nome proprio)", "VERB(Verbo principale)", "NOUN(Sostantivo)", "ADP(Preposizione)", "PROPN(Nome proprio)"
XPOS (ISDT): "SP", "V", "S", "E", "SP"
DEP: "Google" è il nsubj (soggetto nominale) del verbo "ha", che è la Root (radice della frase). "sede" è l' obj (oggetto diretto), e "California" è un obl (complemento obliquo) introdotto dalla preposizione "in".
NER: "Google" è un' 🏢 ORG (Organizzazione), "California" è una 🌍 GPE (Entità geopolitica).
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
|
|||||