Semantic Similarity 벤치마크
Semantic Similarity on Annotated corpus for semantic similarity of clinical trial outcomes (expanded corpus)
F1
- 2019-10-17 — BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus"): F1 93.38
| Rank | Model | F1 | Precision | Recall | Paper | Code | Year |
|---|---|---|---|---|---|---|---|
| 1 | BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 93.38 | 92.98 | 93.85 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 2 | SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 91.51 | 91.3 | 91.79 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 3 | SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 90.69 | 89 | 92.54 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 4 | BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.16 | 89.31 | 89.12 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 5 | BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.12 | 88.25 | 90.1 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 6 | BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 93.38 | 92.98 | 93.85 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 7 | SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 91.51 | 91.3 | 91.79 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 8 | SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 90.69 | 89 | 92.54 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 9 | BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.16 | 89.31 | 89.12 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 10 | BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.12 | 88.25 | 90.1 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 11 | BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 93.38 | 92.98 | 93.85 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 12 | SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 91.51 | 91.3 | 91.79 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 13 | SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 90.69 | 89 | 92.54 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 14 | BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.16 | 89.31 | 89.12 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 | |
| 15 | BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus") | 89.12 | 88.25 | 90.1 | Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations | 2019 |