asahi417 commited on
Commit
bb2d883
1 Parent(s): 5849182

model update

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -102,7 +102,7 @@ model-index:
102
  metrics:
103
  - name: Accuracy
104
  type: accuracy
105
- value: 0.5081967213114754
106
  - task:
107
  name: Analogy Questions (NELL-ONE Analogy)
108
  type: multiple-choice-qa
@@ -198,7 +198,7 @@ This model achieves the following results on the relation understanding tasks:
198
  - Accuracy on U4: 0.6157407407407407
199
  - Accuracy on Google: 0.934
200
  - Accuracy on ConceptNet Analogy: 0.3674496644295302
201
- - Accuracy on T-Rex Analogy: 0.5081967213114754
202
  - Accuracy on NELL-ONE Analogy: 0.61
203
  - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-e-semeval2012/raw/main/classification.json)):
204
  - Micro F1 score on BLESS: 0.9213500075335241
 
102
  metrics:
103
  - name: Accuracy
104
  type: accuracy
105
+ value: 0.5191256830601093
106
  - task:
107
  name: Analogy Questions (NELL-ONE Analogy)
108
  type: multiple-choice-qa
 
198
  - Accuracy on U4: 0.6157407407407407
199
  - Accuracy on Google: 0.934
200
  - Accuracy on ConceptNet Analogy: 0.3674496644295302
201
+ - Accuracy on T-Rex Analogy: 0.5191256830601093
202
  - Accuracy on NELL-ONE Analogy: 0.61
203
  - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-nce-e-semeval2012/raw/main/classification.json)):
204
  - Micro F1 score on BLESS: 0.9213500075335241