Summary of multilingual plugins

The table below summarises the multilingual plugins available for Sintelix, their supported text reference types and system limitations.

Table 1: Multilingual plugins

Plugin

Description

Plugin Chinese

Chinese Language Plugin provides Named Entity Extraction support for Chinese (ZH) language documents.

Supported text reference types: Person, Organisation, Location, DateTime (non-Lexical)

System limitations: none

Plugin EU

European Languages Plugin provides Named Entity Extraction support for German (DE), Spanish (ES), French (FR), Italian (IT) and Dutch (NL) documents.

Supported text reference types: Person, Organisation, Location, DateTime, Money, Time, Person-title, Position

System limitations: none

Plugin Finnish

Finnish Morphology Plugin provides Finnish tokenisation and morphological analysis, allowing custom configuration of Finnish entity extraction. It does not extract any entities by itself.

Supported text reference types: none

System limitations: none

Plugin Indonesian (beta)

Indonesian Language Plugin provides Named Entity Extraction for Bahasa Indonesia (ID) language documents.

Supported text reference types: Person, Organisation, Location, Position, Person-title

Plugin Arabic

Arabic Language Plugin provides tokenisation, transliteration and limited entity extraction for Arabic (AR) documents.

Supported text reference types: Person, Organisation, Location

System limitations: this plugin can only be installed on Windows deployments

Plugin Polish

Polish Language Plugin provides morphological analyser and named entity extraction for the Polish (PL) language documents.

Supported text reference types: Person, Organisation, Location, DateTime

System limitations: none

Plugin Russian

Russian Language Plugin provides named entity extraction for the Russian (RU) language documents.

Supported text reference types: Person, Organisation, Location

System limitations: this plugin can only be installed on Windows deployments

 

fontfontfont