resources..russie-ortho-metadata.long-desc.html Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of lang-russian Show documentation

Support for processing Russian documents

The newest version!

A named entity recognition pipeline that identifies basic entity types, such 
as Person, Location, Organization, Money 
amounts, Time and Date expressions. It works on documents
in the Russian language.

This version of the pipeline includes an orthomatcher to perform
basic coreference resolution based on orthographic similarity.





  
    Default annotations
  
  
    :Person
    Standard named entity types
  
  
    :Location
  
  
    :Organization
  
  
    :Date
  
  
    :Address
    Includes email and IP addresses as well as street addresses
  
  
    Additional annotations available if selected
  
  
    :Money
    Monetary amounts
  
  
    :Percent
    Expressions representing percentages
  
  
    :Token
    The individual tokens of the text, with "category" feature for POS
  
  
    :SpaceToken
    The spaces between tokens
  
  
    :Sentence
    Sentences detected by the sentence splitter
  
  
    :Lookup
    Individual gazetteer lookups
  
  
    :MSD
    "Morpho-Syntactic Description" for selected tokens, including features for "lemma" (the base form of inflected words) and "type" (roughly equivalent to a part of speech tag in English, though more complex as it encodes features such as gender, grammatical case, etc.)

Default annotations
`:Person`	Standard named entity types
`:Location`
`:Organization`
`:Date`
`:Address`	Includes email and IP addresses as well as street addresses
Additional annotations available if selected
`:Money`	Monetary amounts
`:Percent`	Expressions representing percentages
`:Token`	The individual tokens of the text, with "category" feature for POS
`:SpaceToken`	The spaces between tokens
`:Sentence`	Sentences detected by the sentence splitter
`:Lookup`	Individual gazetteer lookups
`:MSD`	"Morpho-Syntactic Description" for selected tokens, including features for "lemma" (the base form of inflected words) and "type" (roughly equivalent to a part of speech tag in English, though more complex as it encodes features such as gender, grammatical case, etc.)