FoR-UNL

From UNL Wiki
(Difference between revisions)
Jump to: navigation, search
(Descriptors)
(Assessment)
Line 67: Line 67:
  
 
== Assessment ==
 
== Assessment ==
A '''dictionary entry''' is considered valid if verified by at least one editor.<br />
+
A '''dictionary entry''' is considered valid in MIR and BRUNO if verified by at least one editor.<br />
 
A '''grammar''' is considered valid if its [[F-measure]] for the reference corpus is equal or higher than 0.8.
 
A '''grammar''' is considered valid if its [[F-measure]] for the reference corpus is equal or higher than 0.8.

Revision as of 20:58, 17 September 2012

FRAU (FRAmework of reference for UNL) is a guideline used to describe achievements of natural languages in relation to UNL. It was inspired by the Common European Framework of Reference for Languages (CEFR), and its main goal is to provide a method for assessing the availability and quality of natural language resources inside the UNL framework.

Reference Levels

FRAU divides languages into three broad divisions which can be divided into six levels:

  • A - Basic Level
    • A1 - Breakthrough or beginner
    • A2 - Waystage or elementary
  • B - Intermediate Level
    • B1 - Threshold or intermediate
    • B2 - Vantage or upper intermediate
  • C - Advanced Level
    • C1 - Effective Operational
    • C2 - Mastery

Descriptors

The descriptors below inform what is required for a language to be classified in each level:

Level UNL-NL Dictionary
(entries)
NL-UNL Dictionary
(entries)
UNL-NL Grammar
(sentences)
NL-UNL Grammar
(sentences)
A1 MIR-A1 BRUNO-A1 UC-A1 NC-A1
A2 MIR-A2 BRUNO-A2 UC-A2 NC-A2
B1 MIR-B1 BRUNO-B1 UC-B1 NC-B1
B2 MIR-B2 BRUNO-B2 UC-B2 NC-B2
C1 MIR-C1 BRUNO-C1 UC-C1 NC-C1
C2 MIR-C2 BRUNO-C2 RC-C2 NC-C2

Where:

  • MIR is a project aiming the development of UNL-NL Dictionaries
  • BRUNO is a project aiming the development of NL-UNL Dictionaries
  • UC is the UNL Reference Corpus
  • NC is the NL Reference Corpus

Assessment

A dictionary entry is considered valid in MIR and BRUNO if verified by at least one editor.
A grammar is considered valid if its F-measure for the reference corpus is equal or higher than 0.8.

Software