The Russian Corpus of Linguistic Acceptability (RuCoLA) is built from the ground up under the well-established binary LA approach. RuCoLA consists of 9.8k in-domain sentences from linguistic publications and 3.6k out-of-domain sentence produced by generative models.
Source: RuCoLA: Russian Corpus of Linguistic Acceptability
Image Source: https://arxiv.org/pdf/2210.12814v1.pdf
Variants: RuCoLA
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Linguistic Acceptability | Ru-BERT+TDA | Can BERT eat RuCoLA? Topological … | 2023-04-04 |
| Linguistic Acceptability | Ru-RoBERTa+TDA | Can BERT eat RuCoLA? Topological … | 2023-04-04 |
| Linguistic Acceptability | RemBERT | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | ruBERT | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | ruGPT-3 | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | ruT5 | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | mBERT | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | XLM-R | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
| Linguistic Acceptability | ruRoBERTa | RuCoLA: Russian Corpus of Linguistic … | 2022-10-23 |
Recent papers with results on this dataset: