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 German UPOS tagging now.
| Group | Tag | Meaning | Example |
|---|---|---|---|
| Open Class | ADJ | Adjective | groß, alt, grün, unverständlich, erster |
| ADV | Adverb | sehr, morgen, unten, wo, dort | |
| INTJ | Interjection | pst, aua, bravo, hallo | |
| NOUN | Noun (common) | Mädchen, Katze, Baum, Luft, Schönheit | |
| PROPN | Proper Noun | Maria, Johannes, London, NATO, HBO | |
| VERB | Verb | rennen, rennt, rennend, essen, aß, gegessen | |
| Closed Class | ADP | Adposition | in, zu, während |
| AUX | Auxiliary | ist, hat (getan), wird (tun), sollte (tun) | |
| CONJ | Conjunction | und, oder, aber (Legacy-Tag) | |
| CCONJ | Coordinating Conjunction | und, oder, aber | |
| SCONJ | Subordinating Conjunction | wenn, während, dass | |
| DET | Determiner | ein, eine, der, die, das | |
| NUM | Numeral | 1, 2017, eins, siebenundsiebzig, MMXIV | |
| PART | Particle | 's (Genitiv-Endung), nicht | |
| PRON | Pronoun | ich, du, er, sie, mich, sich, jemand | |
| 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.
German XPOS tags represent a hybrid system that bridges the gap between universal grammatical roles and the specific complexities of the German language. By integrating the Stuttgart-Tübingen-Tagset (STTS) with Penn Treebank logic, these tags provide a high-resolution analysis of every word in a sentence. For a language learner, this system is transformative: it doesn't just label a word as a "verb," but distinguishes between full verbs (VV), auxiliaries (VA), and modals (VM), while identifying their specific state—whether they are finite (FIN), infinitives (INF), or past participles (PP). This detailed mapping makes the underlying logic of German word order and the case system visible, dramatically accelerating your ability to decode and master complex sentence structures.
Try our German XPOS tagging now.
| Category | Tag | Meaning | Example |
|---|---|---|---|
| Verbs & Modals | VVFIN | Finite full verb | ich spreche, er geht |
| VVINF | Full verb, infinitive | sprechen, laufen | |
| VVPP | Full verb, past participle | gesprochen, gegangen | |
| VAFIN | Auxiliary verb, finite | ich habe, er ist | |
| VAINF | Auxiliary verb, infinitive | sein, werden | |
| VAPP | Auxiliary verb, past participle | gewesen, gehabt | |
| VMFIN | Modal verb, finite | ich kann, du musst | |
| VMINF | Modal verb, infinitive | müssen, wollen | |
| VMPP | Modal verb, past participle | gemusst, gekonnt | |
| VVIZU | Full verb, infinitive with 'zu' | anzusprechen, einzukaufen | |
| VB | Verb, base form (General) | essen, sehen | |
| VBD | Verb, past tense (General) | aß, ging | |
| VBG | Verb, gerund or present participle | essend, gehend | |
| VBN | Verb, past participle (General) | gegessen, gesehen | |
| VBP | Verb, non-3rd person singular present | ich esse, wir trinken | |
| VBZ | Verb, 3rd person singular present | er isst, sie trinkt | |
| MD | Modal (General) | könnte, sollte, wird | |
| Nouns & Adjectives | NE | Proper noun (German STTS) | Berlin, Hans, BMW |
| NN | Noun, singular or mass | Hund, Wasser, Tisch | |
| NNS | Noun, plural (General) | Hunde, Katzen, Bücher | |
| NNP | Proper noun, singular (General) | München, Maria | |
| NNPS | Proper noun, plural (General) | Niederlande, Alpen | |
| ADJA | Adjective, attributive (German) | die gute Frau, ein rotes Haus | |
| ADJD | Predicative or adverbial adjective | sie ist gut, er läuft schnell | |
| JJ | Adjective (General) | glücklich, grün | |
| JJR | Adjective, comparative (General) | glücklicher, grüner | |
| JJS | Adjective, superlative (General) | am glücklichsten, am grünsten | |
| ART | Determiner (article) | der, die, das, ein | |
| Pronouns & Determiners | PPER / PRP | Personal pronoun | ich, du, er, sie, es |
| PRF | Reflexive personal pronoun | sich, mich, dich | |
| PPOSAT / PRP$ | Possessive pronoun (Attributive) | mein Buch, sein Auto | |
| PPOSS | Substantivic possessive pronoun | das ist meins, das ist deins | |
| PDS | Substantivic demonstrative pronoun | das ist gut, dieser ist alt | |
| PDAT | Attributive demonstrative pronoun | dieses Buch, jene Frau | |
| PIS | Substantivic indefinite pronoun | alle kommen, jemand ruft | |
| PIAT | Attributive indefinite pronoun | kein Geld, viele Leute | |
| PRELS | Substantivic relative pronoun | der Mann, der dort steht | |
| PRELAT | Attributive relative pronoun | die Frau, deren Kind spielt | |
| PWS / WP | Interrogative/Wh-pronoun | wer, was | |
| PWAV | Adverbial interrogative pronoun | wo, warum, wie | |
| PAV | Pronominal adverb | dafür, woran, damit | |
| WP$ | Possessive wh-pronoun | wessen | |
| DT | Determiner (General) | der, ein, jener | |
| WDT | Wh-determiner (General) | welcher, welche | |
| PDT | Predeterminer (General) | alle (die), beide (die) | |
| EX | Existential there | es (gibt) | |
| POS | Possessive ending (General) | (beim Genitiv) Marias Buch | |
| Adverbs | RB | Adverb (General) | schnell, sehr, oft |
| RBR | Adverb, comparative | schneller, öfter | |
| RBS | Adverb, superlative | am schnellsten | |
| WRB | Wh-adverb | wann, wieso | |
| Adpositions & Particles | APPR / IN | Preposition | in, von, nach, über |
| APPRART | Preposition with fused article | im, zum, am, ans, ins | |
| APPO | Postposition | den Fluss entlang, der Sache wegen | |
| APZR | Right part of a circumposition | von nun an, um des Friedens willen | |
| PTKVZ / RP | Separable verb prefix / Particle | aufstehen, abfahren / raus | |
| PTKANT | Answer particle | ja, nein, doch, danke | |
| PTKA | Particle modifying adjective/adverb | am besten, zu schnell, allzu | |
| TO | to (General) | zu (essen), um... zu | |
| Conjunctions | CC | Coordinating conjunction | und, oder, aber |
| KOUI | Subord. conj. with 'zu' + infinitive | um... zu, ohne... zu | |
| KOUS | Subord. conj. with clause | dass, weil, wenn, ob | |
| KOKOM | Comparison particle | als, wie | |
| Special & Numbers | CD | Cardinal number | eins, zwei, 5 |
| TRUNC | Truncated word | An- (und Verkauf), Erdbeer- (und Himbeereis) | |
| UH | Interjection | hallo, ach, aua, oh | |
| LS | List item marker | 1., a) |
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 isst. |
| csubj | Clausal subject | Was er tat, war falsch. | |
| obj | Direct object | Ich sehe den Mond. | |
| iobj | Indirect object | Sie gab mir ein Geschenk. | |
| ccomp | Clausal complement (finite) | Er sagte, er sei müde. | |
| xcomp | Open clausal complement | Ich will gehen. | |
| Non-Core Dependents | obl | Oblique nominal | Er saß auf dem Stuhl. |
| vocative | Vocative | Johannes, komm hierher! | |
| expl | Expletive | Da ist eine Katze. | |
| dislocated | Dislocated element | Dieser Mann, ich kenne ihn. | |
| advcl | Adverbial clause modifier | Ich ging, nachdem er ankam. | |
| advmod | Adverbial modifier | Lauf schnell. | |
| discourse | Discourse element | Nun, ich bin nicht sicher. | |
| aux | Auxiliary | Ich kann sehen. | |
| cop | Copula | Sie ist glücklich. | |
| mark | Subordinating marker | Ich weiß, dass du es weißt. | |
| Nominal Dependents | nmod | Nominal modifier | Die Tür des Autos. |
| appos | Appositional modifier | Sam, mein Freund. | |
| nummod | Numeric modifier | Sieben Tage. | |
| acl | Adjectival clause | Der Plan zu gewinnen. | |
| amod | Adjectival modifier | Der blaue Himmel. | |
| det | Determiner | Das Ende. | |
| case | Case marking | Der König von Frankreich. | |
| fixed | Fixed multiword expression | Trotz allem. | |
| flat | Flat multiword name | Stadt München. | |
| compound | Compound noun | Telefonzelle. | |
| list | List element | Telefon, Schlüssel, Brieftasche. | |
| Coordination | conj | Conjunct | Brot und Butter. |
| cc | Coordinating conjunction | Brot und Butter. | |
| Special Labels | aux:pass | Passive auxiliary | Es wurde gestohlen. |
| punct | Punctuation | Hallo! | |
| dep | Unspecified dependency | (Wird für unbekannte Verknüpfungen verwendet) | |
| ROOT | Root of the sentence | Ich aß zu Mittag. |
| Attachment | Full Name | Explanation | Example |
|---|---|---|---|
| :pass | Passive | Indicates a relationship in a passive voice construction. | nsubj:pass (Das Fenster wurde zerbrochen) |
| :nn | Noun Compound | Indicates that a noun is modifying another noun in a compound structure. | compound:nn (Telefonladegerät) |
| :prep | Prepositional | Refines a modifier governed specifically by a preposition. | nmod:prep (Die Katze auf der Matte) |
| :assmod | Associative Modifier | Common in Romanian/Baltic languages; shows nouns modifying other nouns. | nmod:assmod (Das Auto meines Vaters) |
| :poss | Possessive | Indicates ownership or a possessive relationship. | nmod:poss (Mein Hund, Johannes' Hut) |
| :relcl | Relative Clause | Identifies a clause that modifies a noun phrase. | acl:relcl (Das Buch, das ich las) |
| :tmod | Temporal Modifier | A modifier specifically describing time or duration. | nmod:tmod (Ich gehe am Dienstag) |
| :prt | Particle | Used for phrasal verb particles. | compound:prt (Gib auf, fahre herunter) |
| :rcomp | Relative Complement | Used for complements of relative clauses (common in Dutch). | advcl:rcomp (Der Mann, der ging) |
| :flat | Flat Modifier | Used for multi-word expressions that don't have a clear internal head. | flat:name (Präsident 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) | Deutschland, Berlin, Frankreich, Bayern |
| 🏔️ LOC | Non-political location (mountains, rivers) | Pazifischer Ozean, Mount Everest, Die Alpen |
| 🏢 FAC | Facility (buildings, airports, highways) | Brandenburger Tor, Flughafen Berlin Brandenburg, Kölner Dom |
| 👤 PERSON | People (real or fictional) | Angela Merkel, Harry Potter, Albert Einstein |
| 🚩 NORP | Nationalities, religious or political groups | Deutscher, Buddhist, Sozialdemokraten, Japaner |
| 🏢 ORG | Organizations (companies, institutions) | Google, Vereinte Nationen, Siemens, FIFA |
| 📅 DATE | Absolute or relative dates | 4. Juli, 2026, gestern, nächste Woche |
| ⌚ TIME | Times smaller than a day | 9:30 Uhr, Sonnenuntergang, zehn Minuten |
| 🎊 EVENT | Named events (wars, festivals) | Zweiter Weltkrieg, Oktoberfest, Olympische Spiele |
| 💰 MONEY | Monetary values, including unit | 100 €, 5 Millionen Euro, 50 £ |
| ‱ PERCENT | Percentage, including "%" | 20%, achtzig Prozent, 0,5% |
| ⚖️ QUANTITY | Measurements (weight, distance) | 5 km, 50 kg, 30 Quadratmeter |
| 🔢 ORDINAL | "First", "second", etc. | erstens, 2., neunte |
| 🔢 CARDINAL | Numbers not classified elsewhere | 10, eintausend, drei |
| 📦 PRODUCT | Objects, vehicles, foods, etc. (not services) | iPhone, Volkswagen Golf, Coca-Cola |
| 🎨 WORK_OF_ART | Titles of books, songs, etc. | Mona Lisa, Ode an die Freude, Faust |
| 📜 LAW | Named legal documents | Das Grundgesetz, Versailler Vertrag |
| 🗣️ LANGUAGE | Named languages | Deutsch, Python, Mandarin |
Wenn wir den Satz „Google hat seinen Sitz in München“ verarbeiten, sehen die Ebenen wie folgt aus:
Lemma: "Google", "haben", "sein", "Sitz", "in", "München"
UPOS: "PROPN(Eigenname)", "VERB(Verb)", "DET(Determinativ)", "NOUN(Substantiv)", "ADP(Präposition)", "PROPN(Eigenname)"
XPOS: "NE(Eigenname)", "VVFIN(Finites Vollverb)", "PPOSAT(Attributives Possessivpronomen)", "NN(Gattungsname)", "APPR(Präposition)", "NE(Eigenname)"
DEP: „Google“ ist das nsubj (Subjekt) des Verbs „hat“, welches das Root (Satzwurzel) des Satzes ist. „Sitz“ ist das obj (Akkusativobjekt). „München“ ist ein obl (adverbiale Bestimmung) verbunden durch die Präposition „in“.
NER: „Google“ ist ein 🏢 ORG (Organisation), „München“ ist eine 🌍 GPE (Geopolitische Entität).
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
|
|||||