| Benchmark | Model | Rank | Results |
|---|---|---|---|
| natural-language-understanding-on-pdp60 | Word-level CNN+LSTM (full scoring) | #5 | Accuracy: 60.0 |
| natural-language-understanding-on-pdp60 | Word-level CNN+LSTM (partial scoring) | #7 | Accuracy: 53.3 |
| coreference-resolution-on-winograd-schema-challenge | Ensemble of 14 LMs | #39 | Accuracy: 63.7 |
| coreference-resolution-on-winograd-schema-challenge | Word-level CNN+LSTM (partial scoring) | #41 | Accuracy: 62.6 |
| coreference-resolution-on-winograd-schema-challenge | Char-level CNN+LSTM (partial scoring) | #52 | Accuracy: 57.9 |