|
Type or paste a German text into the input box above.
Select a POS analyzer from the left column, then click the "Go" button.
| Example German Text for POS Analysis |
⬆️ |
Die ganze Stadt ist ein Startup: Shenzhen ist das Silicon Valley für Hardware-Firmen.
Wie deutsche Startups die Technologie vorantreiben wollen: Künstliche Intelligenz.
Trend zum Urlaub in Deutschland beschert Gastwirten mehr Umsatz.
Bundesanwaltschaft erhebt Anklage gegen mutmaßlichen Schweizer Spion.
San Francisco erwägt Verbot von Lieferrobotern.
Autonome Fahrzeuge verlagern Haftpflicht auf Hersteller.
Wo bist du?
Was ist die Hauptstadt von Deutschland?
A part of speech is a category that describes the role a word plays in a sentence.
Improving German language learning using Part-of-Speech (POS) tagging involves leveraging syntactic and morphological information to understand sentence structure, disambiguate word meanings, and master inflectional rules.
- German Part-of-Speech
-
UPOS of German
UPOS (Universal POS) is a Coarse-grained and simplified tag that work consistently across all languages. They are shown in the following format.
Headword lemma UPOS DEP 👤NER
-
XPOS of German
XPOS (Detailed POS) is a Fine-Grained tag specific to the German language and the German training data. They are shown in the following format.
Headword lemma XPOS DEP 👤NER
Headword : Headwords are displayed in bold.
lemma : The dictionary form or "root" of a German word. It removes grammatical variations. The lemma is only displayed if the headword is not equal to the lemma.
UPOS : Universal Part-of-Speech. A coarse-grained, standardized tag (like NOUN, VERB, or ADJ) designed to work across all human languages. See examples
XPOS : Language-Specific Part-of-Speech. A fine-grained tag specific to a particular German language’s grammar (e.g., distinguishing a plural noun from a singular noun, etc). See examples
DEP : Dependency. The grammatical relationship between words. It shows how words depend on one another, such as identifying which word is the subject (nsubj) or the direct object (obj). See examples
👤NER : Named Entity Recognition. The identification of ""real-world"" entities within the text, such as People (PER), Locations (GPE), Organizations (ORG), or Dates. See examples
|