research-backup
/

relbert-roberta-large-iloob-a-semeval2012

Feature Extraction

Inference Endpoints

Model card Files Files and versions Community

asahi417 commited on Feb 10, 2023

Commit

59242b8

•

1 Parent(s): 30d6e83

model update

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -102,7 +102,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6502732240437158
   - task:
       name: Analogy Questions (NELL-ONE Analogy)
       type: multiple-choice-qa
@@ -198,7 +198,7 @@ This model achieves the following results on the relation understanding tasks:
     - Accuracy on U4: 0.5856481481481481
     - Accuracy on Google: 0.914
     - Accuracy on ConceptNet Analogy: 0.46057046979865773
-    - Accuracy on T-Rex Analogy: 0.6502732240437158
     - Accuracy on NELL-ONE Analogy: 0.6183333333333333
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-iloob-a-semeval2012/raw/main/classification.json)):
     - Micro F1 score on BLESS: 0.9180352568931747

     metrics:
     - name: Accuracy
       type: accuracy
+      value: 0.639344262295082
   - task:
       name: Analogy Questions (NELL-ONE Analogy)
       type: multiple-choice-qa
     - Accuracy on U4: 0.5856481481481481
     - Accuracy on Google: 0.914
     - Accuracy on ConceptNet Analogy: 0.46057046979865773
+    - Accuracy on T-Rex Analogy: 0.639344262295082
     - Accuracy on NELL-ONE Analogy: 0.6183333333333333
 - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-iloob-a-semeval2012/raw/main/classification.json)):
     - Micro F1 score on BLESS: 0.9180352568931747