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 Croatian UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | velik, star, zelen, neshvatljiv, prvi |
| ADV | Adverb | vrlo, sutra, dolje, gdje, tamo | |
| INTJ | Interjection | pst, joj, bravo, pozdrav | |
| NOUN | Noun (common) | djevojka, mačka, stablo, zrak, ljepota | |
| PROPN | Proper Noun | Marija, Ivan, London, NATO, HBO | |
| VERB | Verb | trčati, trči, trčanje, jesti, jeo, pojeden | |
| Closed Class | ADP | Adposition | u, prema, tijekom |
| AUX | Auxiliary | jest, učinio je, učinit će, trebao bi | |
| CONJ | Conjunction | i, ili, ali (naslijeđena oznaka) | |
| CCONJ | Coordinating Conjunction | i, ili, ali | |
| SCONJ | Subordinating Conjunction | ako, dok, da | |
| DET | Determiner | jedan, neki, taj (članovi) | |
| NUM | Numeral | 1, 2017, jedan, sedamdeset sedam, MMXIV | |
| PART | Particle | ne, nije | |
| PRON | Pronoun | ja, ti, on, ona, ja sam, oni sami, netko | |
| 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.
The Croatian XPOS tags are based on the MULTEXT-East (MSD) system. Each character in a tag like Ncfsn represents a specific morphological feature (Category, Type, Gender, Number, Case, etc.). Because Croatian is a highly inflected Slavic language, there are thousands of unique combinations. For instance, the distinction between animate (y) and inanimate (n) in the Accusative case is vital for correct noun-adjective agreement.
Try our Croatian XPOS tagging now.
| Group | Position | Category | Label | Meaning |
|---|---|---|---|---|
| Core Category (Pos 1) | 1 | All | N | Noun (Imenica) |
| V | Verb (Glagol) | |||
| A | Adjective (Pridjev) | |||
| P | Pronoun (Zamjenica) | |||
| R | Adverb (Prilog) | |||
| S | Preposition (Prijedlog) | |||
| Nominal (N / A) | 2 | Type | c / p / g / s | Common, Proper / General, Possessive |
| 3 | Gender / Degree | m, f, n / p, c, s | Masculine, Feminine, Neuter / Positive, Comp, Super | |
| 4 | Number / Gender | s, p / m, f, n | Singular, Plural / (Gender for Adjectives) | |
| 5 | Case / Number | n, g, d, a | Nom, Gen, Dat, Acc | |
| l, i, v | Loc, Inst, Voc | |||
| s, p | (Number for Adjectives) | |||
| 6 | Animacy / Case | n, y / n...v | Inanimate, Animate / (Case for Adjectives) | |
| 7 | Definiteness | n, y | Indefinite, Definite (Adjectives only) | |
| Verbal (V) | 2 | Type | m / a / x | Main / Auxiliary / Modal |
| 3 | Form/Mood | r | Present (Prezent) | |
| n / m | Infinitive / Imperative | |||
| l / p | Past Participle / Present Participle | |||
| i / s | Imperfect / Aorist | |||
| 4 | Tense | - | (Usually hyphenated in MSD v4) | |
| 5 | Person | 1, 2, 3 | First, Second, Third Person | |
| 6 | Number | s, p | Singular, Plural | |
| Preposition (S) | 2 | Case | g, d, a, l, i | The case governed by the preposition |
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 jede. |
| csubj | Clausal subject | Ono što je učinio bilo je pogrešno. | |
| obj | Direct object | Vidim mjesec. | |
| iobj | Indirect object | Dala mi je dar. | |
| ccomp | Clausal complement (finite) | Rekao je da je umoran. | |
| xcomp | Open clausal complement | Želim ići. | |
| Non-Core Dependents | obl | Oblique nominal | Sjedio je na stolici. |
| vocative | Vocative | Ivane, dođi ovamo! | |
| expl | Expletive | Tamo je mačka. | |
| dislocated | Dislocated element | Tog čovjeka, njega znam. | |
| advcl | Adverbial clause modifier | Otišao sam nakon što je on stigao. | |
| advmod | Adverbial modifier | Trči brzo. | |
| discourse | Discourse element | Pa, nisam siguran. | |
| aux | Auxiliary | Ja mogu vidjeti. | |
| cop | Copula | Ona je sretna. | |
| mark | Subordinating marker | Znam da znaš. | |
| Nominal Dependents | nmod | Nominal modifier | Vrata automobila. |
| appos | Appositional modifier | Sam, moj prijatelj. | |
| nummod | Numeric modifier | Sedam dana. | |
| acl | Adjectival clause | Plan za pobjedu. | |
| amod | Adjectival modifier | Plavo nebo. | |
| det | Determiner | Kraj. | |
| case | Case marking | Kralj Francuske. | |
| fixed | Fixed multiword expression | Usprkos tome. | |
| flat | Flat multiword name | Grad Zagreb. | |
| compound | Compound noun | Telefonska govornica. | |
| list | List element | Telefon, ključevi, novčanik. | |
| Coordination | conj | Conjunct | Kruh i maslac. |
| cc | Coordinating conjunction | Kruh i maslac. | |
| Special Labels | aux:pass | Passive auxiliary | Bilo je ukradeno. |
| punct | Punctuation | Pozdrav! | |
| dep | Unspecified dependency | (Koristi se za nepoznate veze) | |
| ROOT | Root of the sentence | Jeo sam ručak. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Prozor je bio razbijen) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Punjač za mobitel) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Mačka na prostirci) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Auto mog oca) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Moj pas, Ivanov šešir) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Knjiga koju sam čitao) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Odlazim u utorak) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Odustani, ugasi) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Čovjek koji je otišao) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Predsjednik 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) | Hrvatska, Zagreb, Francuska, Kalifornija |
| 🏔️ LOC | Non-political location (mountains, rivers) | Jadransko more, Mount Everest, Alpe |
| 🏢 FAC | Facility (buildings, airports, highways) | Dubrovačke zidine, Zračna luka Zagreb, Burj Khalifa |
| 👤 PERSON | People (real or fictional) | Nikola Tesla, Harry Potter, Ruđer Bošković |
| 🚩 NORP | Nationalities, religious or political groups | Hrvat, budist, demokrati, Japanac |
| 🏢 ORG | Organizations (companies, institutions) | Google, Ujedinjeni narodi, Rimac Automobili, FIFA |
| 📅 DATE | Absolute or relative dates | 4. srpnja, 2026., jučer, sljedeći tjedan |
| ⌚ TIME | Times smaller than a day | 9:30 ujutro, zalazak sunca, deset minuta |
| 🎊 EVENT | Named events (wars, festivals) | Drugi svjetski rat, Ultra Europe, Olimpijske igre |
| 💰 MONEY | Monetary values, including unit | 100 $, 5 milijuna eura, 50 £ |
| ‱ PERCENT | Percentage, including "%" | 20%, osamdeset posto, 0,5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5 km, 50 kg, 30 četvornih metara |
| 🔢 ORDINAL | "First", "second", etc. | prvi, 2., deveti |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, tisuću, tri |
| 📦 PRODUCT | Objects, vehicles, foods, etc. (not services) | iPhone, Rimac Nevera, Coca-Cola |
| 🎨 WORK_OF_ART | Titles of books, songs, etc. | Mona Lisa, Bohemian Rhapsody, Hamlet |
| 📜 LAW | Named legal documents | Ustav Republike Hrvatske, Versajski ugovor |
| 🗣️ LANGUAGE | Named languages | Hrvatski, Python, engleski |
Ako obradimo rečenicu „Google ima sjedište u Zagrebu“ (Google is based in Zagreb), slojevi izgledaju ovako:
Lemma (Lema): "Google", "imati", "sjedište", "u", "Zagreb"
UPOS (Univerzalne oznake vrsta riječi): "PROPN(Vlastita imenica)", "VERB(Glagol)", "NOUN(Opća imenica)", "ADP(Prijedlog)", "PROPN(Vlastita imenica)"
XPOS (Specifične oznake vrsta riječi/MSD): "Npmsn(Vlastita imenica, muški rod, jednina, nominativ)", "Vmr3s(Glagol, prezent, 3. lice, jednina)", "Ncnsa(Opća imenica, srednji rod, jednina, akuzativ)", "Sl(Prijedlog, vlada lokativom)", "Npmsl(Vlastita imenica, muški rod, jednina, lokativ)"
DEP (Sintaktičke zavisnosti): „Google“ je nsubj (nominalni subjekt) glagola „ima“ koji predstavlja Root (korijen rečenice). „sjedište“ je obj (izravni objekt). „Zagrebu“ je obl (adverbni modifikator) povezan preko prijedloga „u“.
NER (Prepoznavanje imenovanih entiteta): „Google“ je 🏢 ORG (Organizacija), a „Zagrebu“ je 🌍 GPE (Geopolitički entitet).
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
|
|||||