Language Modelling on Annotated corpus for semantic similarity of clinical trial outcomes (original corpus)

Metric: Recall (higher is better)

LeaderboardDataset

Results

Submit a result

Sort:

#	Model↕	Recall▼	Extra Data	Paper	Date↕	Code
1	SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	91.53	No	-	-	-
2	SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	90.78	No	-	-	-
3	BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	90.76	No	-	-	-
4	BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	88.15	No	-	-	-
5	BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	85.2	No	-	-	-

#1SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")
91.53
Recall
No paper
#2SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")
90.78
Recall
No paper
#3BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")
90.76
Recall
No paper
#4BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")
88.15
Recall
No paper
#5BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")
85.2
Recall
No paper