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 Learningβwhere 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 Tagalog UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | malaki, matanda, berde, hindi maunawaan, una |
| ADV | Adverb | napaka, bukas, pababa, saan, doon | |
| INTJ | Interjection | psst, aray, bravo, kumusta | |
| NOUN | Noun (common) | babae, pusa, puno, hangin, kagandahan | |
| PROPN | Proper Noun | Maria, Juan, London, NATO, HBO | |
| VERB | Verb | tumakbo, tumatakbo, tumatakbo, kumain, kumain, kinain | |
| Closed Class | ADP | Adposition | sa, patungo sa, sa panahon ng |
| AUX | Auxiliary | ay, mayroon, gagawin, dapat | |
| CONJ | Conjunction | at, o, ngunit (legacy tag) | |
| CCONJ | Coordinating Conjunction | at, o, ngunit | |
| SCONJ | Subordinating Conjunction | kung, habang, na | |
| DET | Determiner | isang, ang | |
| NUM | Numeral | 1, 2017, isa, pitumpu't pito, MMXIV | |
| PART | Particle | ng, hindi | |
| PRON | Pronoun | ako, ikaw, siya, siya, sarili ko, sarili nila, mayroon | |
| Other | PUNCT | Punctuation | ., (, ), ?, ] |
| SYM | Symbol | $, %, +, β, :), π» | |
| 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 languageβensuring 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 Tagalog XPOS system for the CalamanCy models follows a nomenclature where the primary category (UPOS) is often preserved, but extended with functional markers. In Tagalog, markers like ang, ng, and sa are vital for defining the role of nouns and verbs. The _PART suffix typically refers to particles (like linkers na/-ng or enclitic particles like ba, pa) when they are grammatically associated with a specific word class.
Try our Tagalog XPOS tagging now.
| Group | Tag | Meaning / Description | Example |
|---|---|---|---|
| Nouns & Proper Names | NOUN | Common Noun | bata (child), bahay (house) |
| NOUN_PART | Particle associated with a Noun phrase | ang, ng, mga | |
| PROPN | Proper Noun | Juan, Pilipinas, Manila | |
| Verbs | VERB | Main Verb (with aspect/focus) | kumakain (eating), tatakbo |
| VERB_PART | Particle associated with a Verb phrase | ay (inversion), na, pa | |
| AUX | Auxiliary Verb | dapat (must), maaari (can) | |
| Modifiers | ADJ | Adjective | mabilis (fast), maganda |
| ADJ_PART | Particle associated with an Adjective | mas, pinaka (degree markers) | |
| ADV | Adverb | kahapon (yesterday), dito | |
| ADV_PART | Particle associated with an Adverb | nga, din, rin (enclitics) | |
| Pronouns | PRON | Pronoun (Personal, Dem, etc.) | ako (I), ikaw, ito, iyan |
| PRON_PART | Particle associated with a Pronoun | si (personal marker) | |
| Functional Categories | ADP | Adposition (Prepositions) | sa, para sa, tungkol sa |
| SCONJ | Subordinating Conjunction | dahil (because), kung (if) | |
| CCONJ | Coordinating Conjunction | at (and), o (or), ngunit | |
| DET | Determiner | yung, bawat (each) | |
| PART | General Particle | na (linker), ba (interrogative) | |
| NUM | Numeral | isa (one), dalawa, 2024 | |
| Others | INTJ | Interjection | hala!, aray!, naku! |
| PUNCT | Punctuation | ., ,, !, ? | |
| SYM | Symbol | $, %, @ | |
| X | Other / Foreign / Unknown | computer, download |
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 | Kumakain si Elon. |
| csubj | Clausal subject | Mali ang kanyang ginawa. | |
| obj | Direct object | Nakikita ko ang buwan. | |
| iobj | Indirect object | Binigyan niya ako ng regalo. | |
| ccomp | Clausal complement (finite) | Sinabi niyang napagod siya. | |
| xcomp | Open clausal complement | Gusto kong pumunta. | |
| Non-Core Dependents | obl | Oblique nominal | Umupo siya sa upuan. |
| vocative | Vocative | Juan, halika rito! | |
| expl | Expletive | May pusa doon. | |
| dislocated | Dislocated element | Kilala ko ang lalaking iyon. | |
| advcl | Adverbial clause modifier | Umalis ako pagkarating niya. | |
| advmod | Adverbial modifier | Tumakbo nang mabilis. | |
| discourse | Discourse element | Buweno, hindi ako sigurado. | |
| aux | Auxiliary | Kaya kong makakita. | |
| cop | Copula | Siya ay masaya. | |
| mark | Subordinating marker | Alam ko na alam mo. | |
| Nominal Dependents | nmod | Nominal modifier | Pinto ng kotse. |
| appos | Appositional modifier | Sam, na aking kaibigan. | |
| nummod | Numeric modifier | Pitong araw. | |
| acl | Adjectival clause | Ang planong manalo. | |
| amod | Adjectival modifier | Ang asul na langit. | |
| det | Determiner | Ang wakas. | |
| case | Case marking | Ang hari ng Pransya. | |
| fixed | Fixed multiword expression | Sa kabila ng iyon. | |
| flat | Flat multiword name | Lungsod ng New York. | |
| compound | Compound noun | Telepono booth. | |
| list | List element | Telepono, mga susi, pitaka. | |
| Coordination | conj | Conjunct | Tinapay at mantikilya. |
| cc | Coordinating conjunction | Tinapay at mantikilya. | |
| Special Labels | aux:pass | Passive auxiliary | Ito ay ninakaw. |
| punct | Punctuation | Kumusta! | |
| dep | Unspecified dependency | (Ginagamit para sa mga hindi kilalang link) | |
| ROOT | Root of the sentence | Kumain ako ng tanghalian. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Nasira ang bintana) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Charger ng telepono) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Ang pusa sa banig) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Ang kotse ng aking ama) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Ang aking aso, sumbrero ni Juan) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Ang aklat na aking binasa) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Aalis ako sa Martes) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Sumuko, patayin) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Ang lalaking umalis) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Pangulong 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 |
|---|---|---|
| π GPE | Geopolitical entity (countries, cities, states) | Pilipinas, Maynila, Pransya, California |
| ποΈ LOC | Non-political location (mountains, rivers) | Karagatang Pasipiko, Bundok Everest, Ang Alps |
| π’ FAC | Facility (buildings, airports, highways) | Tulay ng Golden Gate, Paliparang Pandaigdig ng Ninoy Aquino, Burj Khalifa |
| π€ PERSON | People (real or fictional) | Elon Musk, Harry Potter, Alan Turing |
| π© NORP | Nationalities, religious or political groups | Amerikano, Budista, mga Demokratiko, Hapones |
| π’ ORG | Organizations (companies, institutions) | Google, United Nations, Apple, FIFA |
| π DATE | Absolute or relative dates | Hulyo 4, 2026, kahapon, susunod na linggo |
| β TIME | Times smaller than a day | 9:30 ng umaga, paglubog ng araw, sampung minuto |
| π EVENT | Named events (wars, festivals) | Ikalawang Digmaang Pandaigdig, Coachella, Palarong Olimpiko |
| π° MONEY | Monetary values, including unit | $100, 5 milyong Euro, Β£50 |
| β± PERCENT | Percentage, including "%" | 20%, walumpung porsyento, 0.5% |
| βοΈ QUANTITY | Measurements (weight, distance) | 5km, 50kg, 30 metro kuwadrado |
| π’ ORDINAL | "First", "second", etc. | una, pangalawa, pangsiyam |
| π’ CARDINAL | Numbers not classified elsewhere | 10, isang libo, tatlo |
| π¦ PRODUCT | Objects, vehicles, foods, etc. (not services) | iPhone, Tesla Model S, Coca-Cola |
| π¨ WORK_OF_ART | Titles of books, songs, etc. | Mona Lisa, Bohemian Rhapsody, Hamlet |
| π LAW | Named legal documents | Ang Saligang Batas, Kasunduan sa Versailles |
| π£οΈ LANGUAGE | Named languages | Tagalog, Python, Mandarin |
Kung ipaproseso natin ang pariralang "Ang Google ay nakabase sa California" (Google is based in California), ganito ang hitsura ng mga layer:
Lemma: "Ang", "Google", "ay", "nakabase", "sa", "California"
UPOS: "ADP(Adposition/Marker)", "PROPN(Pangngalang Pantangi)", "AUX(Auxiliary)", "VERB(Pandiwa)", "ADP(Adposition)", "PROPN(Pangngalang Pantangi)"
XPOS (CalamanCy): "NOUN_PART", "PROPN", "AUX", "VERB", "ADP", "PROPN"
DEP: Ang "Google" ay ang nominal na paksa (nsubj:pass) ng pandiwang "nakabase" na siyang Root (ugat ng pangungusap). Ang "ay" ay ang auxiliary (aux). Ang "California" ay ang obl (oblique argument) na konektado ng marker na "sa".
NER: Ang "Google" ay isang π’ ORG (Organisasyon), ang "California" ay isang π GPE (Geopolitical Entity).
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
|
|||||