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 Latin UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | magnus, senex, viridis, incomprehensibilis, primus |
| ADV | Adverb | valde, cras, deorsum, ubi, ibi | |
| INTJ | Interjection | st, hei, euge, salve | |
| NOUN | Noun (common) | puella, feles, arbor, aer, pulchritudo | |
| PROPN | Proper Noun | Maria, Iohannes, Londinium, NATO, HBO | |
| VERB | Verb | currere, currit, currens, edere, edit, esum | |
| Closed Class | ADP | Adposition | in, ad, durante |
| AUX | Auxiliary | est, habet, faciet, debet | |
| CONJ | Conjunction | et, vel, sed (legacy tag) | |
| CCONJ | Coordinating Conjunction | et, vel, sed | |
| SCONJ | Subordinating Conjunction | si, dum, quod | |
| DET | Determiner | —, —, — | |
| NUM | Numeral | 1, 2017, unus, septuaginta septem, MMXIV | |
| PART | Particle | —, non | |
| PRON | Pronoun | ego, tu, is, ea, egomet, se, aliquis | |
| 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.
Latin XPOS tags in the ITTB system are modular. They consist of a Primary Category (identifying the word class and inflectional group) and Morphological Features (separated by pipes, e.g., N1|casA|gen2). The codes below allow for precise decoding of every grammatical attribute of a Latin token.
Try our Latin XPOS tagging now.
| Category | Tag | Meaning | Example |
|---|---|---|---|
| Nouns | N1 | 1st Declension | aqua (water) |
| N2 | 2nd Declension | dominus (lord) | |
| N3 | 3rd Declension | corpus (body) | |
| N4 | 4th Declension | manus (hand) | |
| N5 | 5th Declension | res (thing) | |
| Adjectives | A1 | 1st/2nd Declension | magnus (great) |
| A3 | 3rd Declension | omnis (all) | |
| Verbs | V5 | 1st Conjugation (-are) | amare (to love) |
| V6 | 2nd Conjugation (-ere) | videre (to see) | |
| V7 | 3rd Conjugation (-ere/-io) | facere (to do) | |
| V8 | 4th Conjugation (-ire) | audire (to hear) | |
| Pronouns | S1 | Pronoun/Pronominal Adj | qui (who) |
| Adverbs | D1 | Adverb | bene (well) |
| Prepositions | P1 | Preposition | ad (to) |
| Conjunctions | C1 | Conjunction | et (and) |
| Numerals | O | Numeral/Symbol | unus (one) |
| Case (cas) | casA / casJ | Nominative S/P | -a, -us, -is |
| casB / casK | Genitive S/P | -ae, -i, -is | |
| casC / casL | Dative S/P | -ae, -o, -i | |
| casD / casM | Accusative S/P | -am, -um, -em | |
| casE / casO | Ablative S/P | -a, -o, -e | |
| casF | Vocative | -a, -e | |
| Gender (gen) | gen1 | Masculine | dominus |
| gen2 | Feminine | aqua | |
| gen3 | Neuter | bellum | |
| gen6/7 | Common/Ambiguous | canis | |
| Number (num) | num1 | Singular | -us |
| num2 | Plural | -i | |
| Mood (mod) | modA | Indicative | videt |
| modB | Subjunctive | videat | |
| modD | Infinitive | videre | |
| modE | Participle/Gerund | videns | |
| Tense (tem) | tem1 | Present | amat |
| tem2 | Imperfect | amabat | |
| tem4 | Perfect | amavit | |
| tem8 | Future | amabit | |
| Grade (grn) | grn1 | Positive | magnus |
| grn2 | Comparative | maior | |
| grn3 | Superlative | maximus |
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 edit. |
| csubj | Clausal subject | Quod fecit malum erat. | |
| obj | Direct object | Ego video lunam. | |
| iobj | Indirect object | Illa mihi donum dedit. | |
| ccomp | Clausal complement (finite) | Dixit se fessum esse. | |
| xcomp | Open clausal complement | Volo ire. | |
| Non-Core Dependents | obl | Oblique nominal | In sella sedit. |
| vocative | Vocative | Iohannes, veni huc! | |
| expl | Expletive | Feles ibi est. | |
| dislocated | Dislocated element | Illum virum novi. | |
| advcl | Adverbial clause modifier | Discessi postquam venit. | |
| advmod | Adverbial modifier | Curre celeriter. | |
| discourse | Discourse element | Bene, non sum certus. | |
| aux | Auxiliary | Possum videre. | |
| cop | Copula | Illa laeta est. | |
| mark | Subordinating marker | Scio quod scis. | |
| Nominal Dependents | nmod | Nominal modifier | Ostium currūs. |
| appos | Appositional modifier | Samus, amicus meus. | |
| nummod | Numeric modifier | Septem dies. | |
| acl | Adjectival clause | Consilium vincendi. | |
| amod | Adjectival modifier | Caelum caeruleum. | |
| det | Determiner | Finis. | |
| case | Case marking | Rex Franciae. | |
| fixed | Fixed multiword expression | Quamquam id. | |
| flat | Flat multiword name | Urbs Novum Eboracum. | |
| compound | Compound noun | Taberna telephonica. | |
| list | List element | Telephonum, claves, sacculus. | |
| Coordination | conj | Conjunct | Panis et butyrum. |
| cc | Coordinating conjunction | Panis et butyrum. | |
| Special Labels | aux:pass | Passive auxiliary | Raptum est. |
| punct | Punctuation | Salve! | |
| dep | Unspecified dependency | (Adhibetur pro nexibus ignotis) | |
| ROOT | Root of the sentence | Prandium edi. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Fenestra fracta est) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Onerator telephonicus) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Feles in tapete) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Currus patris mei) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Canis meus, petasus Iohannis) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Liber quem legi) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Die Martis discedam) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Desistere, claudere) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Vir qui discessit) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Praeses 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) | Civitates Foederatae Americae, Novum Eboracum, Gallia, California |
| 🏔️ LOC | Non-political location (mountains, rivers) | Oceanus Pacificus, Mons Everest, Alpes |
| 🏢 FAC | Facility (buildings, airports, highways) | Pons Aeneus, Aeroportus JFK, Burj Khalifa |
| 👤 PERSON | People (real or fictional) | Elon Musk, Harrius Potter, Alanus Turing |
| 🚩 NORP | Nationalities, religious or political groups | Americanus, Buddhista, Democraticae, Iaponicus |
| 🏢 ORG | Organizations (companies, institutions) | Google, Nationes Unitae, Apple, FIFA |
| 📅 DATE | Absolute or relative dates | IV Iulii, MMXXVI, heri, proxima hebdomade |
| ⌚ TIME | Times smaller than a day | hora 9:30 antemeridiana, solis occasus, decem minuta |
| 🎊 EVENT | Named events (wars, festivals) | Secundum Bellum Mundanum, Coachella, Ludi Olympici |
| 💰 MONEY | Monetary values, including unit | $100, V decies centena milia Euronis, £50 |
| ‱ PERCENT | Percentage, including "%" | 20%, octoginta centesimae, 0.5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | V km, C librae, XXX metra quadrata |
| 🔢 ORDINAL | "First", "second", etc. | primus, secundus, nonus |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, mille, tria |
| 📦 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, Hamletus |
| 📜 LAW | Named legal documents | Constitutio, Foedus Versaliis sancitum |
| 🗣️ LANGUAGE | Named languages | Latina, Python, Mandarina |
Si sententiam „Google in California situm est“ (Google is based in California) tractamus, strata sic videntur:
Lemma: "Google", "in", "California", "sino", "sum"
UPOS: "PROPN(Nomen Proprium)", "ADP(Praepositio)", "PROPN(Nomen Proprium)", "VERB(Verbum)", "AUX(Auxiliare)"
XPOS: "N3|stative", "prep", "N1|ablative", "V3|participium", "V5|praesens"
DEP: „Google“ est nsubj:pass (subiectum nominale passivum) verbi „situm“, quod est Root (radix sententiae). „est“ est aux:pass (verbum auxiliare passivum). „California“ est obl (obliquum) per praepositionem „in“ nexum.
NER: „Google“ est 🏢 ORG (Societas), „California“ est 🌍 GPE (Locus geopoliticus).
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
|
|||||