model update
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: Accuracy
|
16 |
type: accuracy
|
17 |
-
value:
|
18 |
- task:
|
19 |
name: Analogy Questions (SAT full)
|
20 |
type: multiple-choice-qa
|
@@ -25,7 +25,7 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
-
value:
|
29 |
- task:
|
30 |
name: Analogy Questions (SAT)
|
31 |
type: multiple-choice-qa
|
@@ -36,7 +36,7 @@ model-index:
|
|
36 |
metrics:
|
37 |
- name: Accuracy
|
38 |
type: accuracy
|
39 |
-
value:
|
40 |
- task:
|
41 |
name: Analogy Questions (BATS)
|
42 |
type: multiple-choice-qa
|
@@ -47,7 +47,7 @@ model-index:
|
|
47 |
metrics:
|
48 |
- name: Accuracy
|
49 |
type: accuracy
|
50 |
-
value:
|
51 |
- task:
|
52 |
name: Analogy Questions (Google)
|
53 |
type: multiple-choice-qa
|
@@ -58,7 +58,7 @@ model-index:
|
|
58 |
metrics:
|
59 |
- name: Accuracy
|
60 |
type: accuracy
|
61 |
-
value:
|
62 |
- task:
|
63 |
name: Analogy Questions (U2)
|
64 |
type: multiple-choice-qa
|
@@ -69,7 +69,7 @@ model-index:
|
|
69 |
metrics:
|
70 |
- name: Accuracy
|
71 |
type: accuracy
|
72 |
-
value:
|
73 |
- task:
|
74 |
name: Analogy Questions (U4)
|
75 |
type: multiple-choice-qa
|
@@ -80,7 +80,7 @@ model-index:
|
|
80 |
metrics:
|
81 |
- name: Accuracy
|
82 |
type: accuracy
|
83 |
-
value:
|
84 |
- task:
|
85 |
name: Lexical Relation Classification (BLESS)
|
86 |
type: classification
|
@@ -160,12 +160,12 @@ RelBERT fine-tuned from [roberta-large](https://huggingface.co/roberta-large) on
|
|
160 |
Fine-tuning is done via [RelBERT](https://github.com/asahi417/relbert) library (see the repository for more detail).
|
161 |
It achieves the following results on the relation understanding tasks:
|
162 |
- Analogy Question ([dataset](https://huggingface.co/datasets/relbert/analogy_questions), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/analogy.json)):
|
163 |
-
- Accuracy on SAT (full):
|
164 |
-
- Accuracy on SAT:
|
165 |
-
- Accuracy on BATS:
|
166 |
-
- Accuracy on U2:
|
167 |
-
- Accuracy on U4:
|
168 |
-
- Accuracy on Google:
|
169 |
- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/classification.json)):
|
170 |
- Micro F1 score on BLESS: None
|
171 |
- Micro F1 score on CogALexV: None
|
@@ -173,7 +173,7 @@ It achieves the following results on the relation understanding tasks:
|
|
173 |
- Micro F1 score on K&H+N: None
|
174 |
- Micro F1 score on ROOT09: None
|
175 |
- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/relation_mapping.json)):
|
176 |
-
- Accuracy on Relation Mapping:
|
177 |
|
178 |
|
179 |
### Usage
|
|
|
14 |
metrics:
|
15 |
- name: Accuracy
|
16 |
type: accuracy
|
17 |
+
value: 0.8933928571428571
|
18 |
- task:
|
19 |
name: Analogy Questions (SAT full)
|
20 |
type: multiple-choice-qa
|
|
|
25 |
metrics:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
+
value: 0.6898395721925134
|
29 |
- task:
|
30 |
name: Analogy Questions (SAT)
|
31 |
type: multiple-choice-qa
|
|
|
36 |
metrics:
|
37 |
- name: Accuracy
|
38 |
type: accuracy
|
39 |
+
value: 0.6884272997032641
|
40 |
- task:
|
41 |
name: Analogy Questions (BATS)
|
42 |
type: multiple-choice-qa
|
|
|
47 |
metrics:
|
48 |
- name: Accuracy
|
49 |
type: accuracy
|
50 |
+
value: 0.8293496386881601
|
51 |
- task:
|
52 |
name: Analogy Questions (Google)
|
53 |
type: multiple-choice-qa
|
|
|
58 |
metrics:
|
59 |
- name: Accuracy
|
60 |
type: accuracy
|
61 |
+
value: 0.958
|
62 |
- task:
|
63 |
name: Analogy Questions (U2)
|
64 |
type: multiple-choice-qa
|
|
|
69 |
metrics:
|
70 |
- name: Accuracy
|
71 |
type: accuracy
|
72 |
+
value: 0.6666666666666666
|
73 |
- task:
|
74 |
name: Analogy Questions (U4)
|
75 |
type: multiple-choice-qa
|
|
|
80 |
metrics:
|
81 |
- name: Accuracy
|
82 |
type: accuracy
|
83 |
+
value: 0.6597222222222222
|
84 |
- task:
|
85 |
name: Lexical Relation Classification (BLESS)
|
86 |
type: classification
|
|
|
160 |
Fine-tuning is done via [RelBERT](https://github.com/asahi417/relbert) library (see the repository for more detail).
|
161 |
It achieves the following results on the relation understanding tasks:
|
162 |
- Analogy Question ([dataset](https://huggingface.co/datasets/relbert/analogy_questions), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/analogy.json)):
|
163 |
+
- Accuracy on SAT (full): 0.6898395721925134
|
164 |
+
- Accuracy on SAT: 0.6884272997032641
|
165 |
+
- Accuracy on BATS: 0.8293496386881601
|
166 |
+
- Accuracy on U2: 0.6666666666666666
|
167 |
+
- Accuracy on U4: 0.6597222222222222
|
168 |
+
- Accuracy on Google: 0.958
|
169 |
- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/classification.json)):
|
170 |
- Micro F1 score on BLESS: None
|
171 |
- Micro F1 score on CogALexV: None
|
|
|
173 |
- Micro F1 score on K&H+N: None
|
174 |
- Micro F1 score on ROOT09: None
|
175 |
- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/roberta-large-semeval2012-average-prompt-d-nce/raw/main/relation_mapping.json)):
|
176 |
+
- Accuracy on Relation Mapping: 0.8933928571428571
|
177 |
|
178 |
|
179 |
### Usage
|