FoR-UNL

From UNL Wiki
Revision as of 15:33, 22 July 2013 by Martins (Talk | contribs)
Jump to: navigation, search

FoR-UNL (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 System.

Reference Levels

The FoR-UNL classifies languages in three broad divisions which can be divided into six levels, according to the recall and precision of the corresponding resources:

  • 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 GD
(entries)
AD
(entries)
ND
(entries)
GG
(sentences)
AG
(sentences)
A1 GD-A1 AD-A1 ND-A1 GG-A1 AG-A1
A2 GD-A2 AD-A2 ND-A2 GG-A2 AG-A2
B1 GD-B1 AD-B1 ND-B1 GG-B1 AG-B1
B2 GD-B2 AD-B2 ND-B2 GG-B2 AG-B2
C1 GD-C1 AD-C1 ND-C1 GG-C1 AG-C1
C2 GD-C2 AD-C2 ND-C2 GG-C2 AG-C2

Where:

  • GD targets the development of Generation (UNL->NL) Dictionaries
  • AD targets the development of Analysis (NL->UNL) Dictionaries
  • ND targets the development of NL Dictionaries
  • GG targets the development of Generation (UNL->NL) Grammar
  • AG targets the development of Anlaysis (NL->UNL) Grammar

Assessment

  • GD, AD, ND: A dictionary is considered completed when all its entries are either valid or reported as underspecified or overspecified.
  • GG, AG: A grammar is consider completed if its F-measure is equal or higher than 0.8.
Software