FoR-UNL
From UNL Wiki
(Difference between revisions)
(→Reference Levels) |
(→Descriptors) |
||
| Line 61: | Line 61: | ||
Where:<br /> | Where:<br /> | ||
| − | *[[MIR]] | + | *[[MIR]] targets the development of UNL-NL Dictionaries |
| − | *[[BRUNO]] | + | *[[BRUNO]] targets the development of NL-UNL Dictionaries |
*[[UC]] is the UNL Reference Corpus | *[[UC]] is the UNL Reference Corpus | ||
*[[NC]] is the NL Reference Corpus | *[[NC]] is the NL Reference Corpus | ||
Revision as of 21:36, 21 September 2012
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 | 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 targets the development of UNL-NL Dictionaries
- BRUNO targets the development of NL-UNL Dictionaries
- UC is the UNL Reference Corpus
- NC is the NL Reference Corpus
Assessment
- MIR: A subproject is considered completed when all its entries are either valid or reported as underspecified or overspecified. A dictionary entry is considered valid in MIR if created and verified both in the UNL-NL Dictionary and in the NL Dictionary.
- BRUNO: A subproject is considered completed when all its entries are valid. A dictionary entry is considered valid in BRUNO if created and verified in the NL Dictionary
- UC: A grammar is consider valid if its F-measure for the UNL Reference Corpus is equal or higher than 0.8.
- NC: A grammar is consider valid if its F-measure for the NL Reference Corpus is equal or higher than 0.8.
