| Paper | Code | Task 1 Accuracy: all | Task 1 Accuracy: general purpose | Task 1 Accuracy: domain specific | Task 2 Accuracy: all | Task 2 Accuracy: general purpose | Task 2 Accuracy: domain specific | Task 3 Accuracy: all | Task 3 Accuracy: general purpose | Task 3 Accuracy: domain specific | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Word Sense Disambiguation with Transformer Models | 77.8 | 75.2 | 81.0 | 71.9 | 77.0 | 65.7 | transformers | 2021-04-30 | ||||
| CTLR@WiC-TSV: Target Sense Verification using Marked Inputs andPre-trained Models | 76.8 | 74.5 | 79.6 | 72.7 | 65.6 | 81.5 | 78.3 | 72.1 | 85.7 | CTLR | 2021-04-30 | |
| GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge | ✓ Link | 75.9 | 75.2 | 76.7 | GlossBert-ws | 2019-08-20 | ||||||
| WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context | ✓ Link | 75.3 | 73.3 | 77.9 | 71.7 | 68.6 | 74.7 | 76.6 | 73.5 | 80.4 | Bert-base | 2020-04-30 |
| WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context | ✓ Link | 54.4 | 49.2 | 60.6 | 62.8 | 57.6 | 69.1 | 60.5 | 54.4 | 67.9 | Unsupervised Bert | 2020-04-30 |
| WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context | ✓ Link | 53.7 | 56.2 | 50.6 | 52.7 | 56.8 | 47.7 | 53.4 | 57.1 | 49.0 | FastText | 2020-04-30 |
| WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context | ✓ Link | 50.8 | 53.8 | 47.0 | 50.8 | 53.8 | 47.0 | 50.8 | 53.8 | 47.0 | All true | 2020-04-30 |
| WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context | ✓ Link | 85.3 | 82.1 | 89.2 | Human | 2020-04-30 |