12 ноября 2020 г. 11:57
Команда AGI NLP
Ссылка на модель https://github.com/RussianNLP/RussianSuperGLUE
| Датасет | Результат | Метрика |
|---|---|---|
| LiDiRus | 0,626 | Кор, коэффициент Мэтью |
| RCB | 0,68 / 0,702 | F1/Точность |
| PARus | 0,982 | Точность |
| MuSeRC | 0,806 / 0,42 | F1a/Em |
| TERRa | 0,92 | Точность |
| RUSSE | 0,805 | Точность |
| RWSD | 0,84 | Точность |
| DaNetQA | 0,915 | Точность |
| RuCoS | 0,93 / 0,89 | F1/EM |
HUMAN BENCHMARK for version 1.2
| Категория | Результат |
|---|---|
| LOGIC | |
| KNOWLEDGE | |
| PREDICATE-ARGUMENT STRUCTURE | |
| LEXICAL SEMANTICS |
| Lexical Semantics - Lexical Entailment | |
|---|---|
| Lexical Semantics - Morphological Negation | |
| Lexical Semantics - Factivity | |
| Lexical Semantics - Symmetry/Collectivity | |
| Lexical Semantics - Redundancy | |
| Lexical Semantics - Named Entities | |
| Lexical Semantics - Quantifiers | |
| Predicate-Argument Structure Core Args | |
| Predicate-Argument Structure Prepositional Phrases | |
| Predicate-Argument Structure Ellipsis/Implicits | |
| Predicate-Argument Structure Anaphora/Coreference | |
| Predicate-Argument Structure Active/Passive | |
| Predicate-Argument Structure Nominalization | |
| Predicate-Argument Structure Genitives/Partitives | |
| Predicate-Argument Structure Datives | |
| Predicate-Argument Structure Relative Clauses | |
| Predicate-Argument Structure Coordination Scopes | |
| Predicate-Argument Structure Intersectivity | |
| Predicate-Argument Structure Restrictivity | |
| Logic Negation | |
| Logic Double Negation | |
| Logic Interval/Numbers | |
| Logic Conjuction | |
| Logic Disjunction | |
| Logic Conditionals | |
| Logic Universal | |
| Logic Existential | |
| Logic Temporal | |
| Logic Upward Monotone | |
| Logic Downward Monotone | |
| Logic Non-Monotonic | |
| Knowledge Common Sense | |
| Knowledge World Knowledge |
| Датасет | Speed | RAM |
|---|---|---|
| LiDiRus | - | - |
| RCB | - | - |
| PARus | - | - |
| MuSeRC | - | - |
| TERRa | - | - |
| RUSSE | - | - |
| RWSD | - | - |
| DaNetQA | - | - |
| RuCoS | - | - |