asahi417 commited on
Commit
d923686
1 Parent(s): 3e826f5

model update

Browse files
Files changed (1) hide show
  1. README.md +232 -0
README.md ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - relbert/semeval2012_relational_similarity
4
+ model-index:
5
+ - name: relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce
6
+ results:
7
+ - task:
8
+ name: Relation Mapping
9
+ type: sorting-task
10
+ dataset:
11
+ name: Relation Mapping
12
+ args: relbert/relation_mapping
13
+ type: relation-mapping
14
+ metrics:
15
+ - name: Accuracy
16
+ type: accuracy
17
+ value: 84.28571428571429
18
+ - task:
19
+ name: Analogy Questions (SAT full)
20
+ type: multiple-choice-qa
21
+ dataset:
22
+ name: SAT full
23
+ args: relbert/analogy_questions
24
+ type: analogy-questions
25
+ metrics:
26
+ - name: Accuracy
27
+ type: accuracy
28
+ value: 0.6122994652406417
29
+ - task:
30
+ name: Analogy Questions (SAT)
31
+ type: multiple-choice-qa
32
+ dataset:
33
+ name: SAT
34
+ args: relbert/analogy_questions
35
+ type: analogy-questions
36
+ metrics:
37
+ - name: Accuracy
38
+ type: accuracy
39
+ value: 0.6142433234421365
40
+ - task:
41
+ name: Analogy Questions (BATS)
42
+ type: multiple-choice-qa
43
+ dataset:
44
+ name: BATS
45
+ args: relbert/analogy_questions
46
+ type: analogy-questions
47
+ metrics:
48
+ - name: Accuracy
49
+ type: accuracy
50
+ value: 0.7865480822679266
51
+ - task:
52
+ name: Analogy Questions (Google)
53
+ type: multiple-choice-qa
54
+ dataset:
55
+ name: Google
56
+ args: relbert/analogy_questions
57
+ type: analogy-questions
58
+ metrics:
59
+ - name: Accuracy
60
+ type: accuracy
61
+ value: 0.93
62
+ - task:
63
+ name: Analogy Questions (U2)
64
+ type: multiple-choice-qa
65
+ dataset:
66
+ name: U2
67
+ args: relbert/analogy_questions
68
+ type: analogy-questions
69
+ metrics:
70
+ - name: Accuracy
71
+ type: accuracy
72
+ value: 0.5394736842105263
73
+ - task:
74
+ name: Analogy Questions (U4)
75
+ type: multiple-choice-qa
76
+ dataset:
77
+ name: U4
78
+ args: relbert/analogy_questions
79
+ type: analogy-questions
80
+ metrics:
81
+ - name: Accuracy
82
+ type: accuracy
83
+ value: 0.6018518518518519
84
+ - task:
85
+ name: Lexical Relation Classification (BLESS)
86
+ type: classification
87
+ dataset:
88
+ name: BLESS
89
+ args: relbert/lexical_relation_classification
90
+ type: relation-classification
91
+ metrics:
92
+ - name: F1
93
+ type: f1
94
+ value: 0.9174325749585657
95
+ - name: F1 (macro)
96
+ type: f1_macro
97
+ value: 0.9108478749677724
98
+ - task:
99
+ name: Lexical Relation Classification (CogALexV)
100
+ type: classification
101
+ dataset:
102
+ name: CogALexV
103
+ args: relbert/lexical_relation_classification
104
+ type: relation-classification
105
+ metrics:
106
+ - name: F1
107
+ type: f1
108
+ value: 0.855868544600939
109
+ - name: F1 (macro)
110
+ type: f1_macro
111
+ value: 0.6923047005195835
112
+ - task:
113
+ name: Lexical Relation Classification (EVALution)
114
+ type: classification
115
+ dataset:
116
+ name: BLESS
117
+ args: relbert/lexical_relation_classification
118
+ type: relation-classification
119
+ metrics:
120
+ - name: F1
121
+ type: f1
122
+ value: 0.6836403033586133
123
+ - name: F1 (macro)
124
+ type: f1_macro
125
+ value: 0.667310500013795
126
+ - task:
127
+ name: Lexical Relation Classification (K&H+N)
128
+ type: classification
129
+ dataset:
130
+ name: K&H+N
131
+ args: relbert/lexical_relation_classification
132
+ type: relation-classification
133
+ metrics:
134
+ - name: F1
135
+ type: f1
136
+ value: 0.9517284551714544
137
+ - name: F1 (macro)
138
+ type: f1_macro
139
+ value: 0.8530904199464412
140
+ - task:
141
+ name: Lexical Relation Classification (ROOT09)
142
+ type: classification
143
+ dataset:
144
+ name: ROOT09
145
+ args: relbert/lexical_relation_classification
146
+ type: relation-classification
147
+ metrics:
148
+ - name: F1
149
+ type: f1
150
+ value: 0.9019116264493889
151
+ - name: F1 (macro)
152
+ type: f1_macro
153
+ value: 0.8996556790705655
154
+
155
+ ---
156
+ # relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce
157
+
158
+ RelBERT fine-tuned from [roberta-large](https://huggingface.co/roberta-large) on
159
+ [relbert/semeval2012_relational_similarity](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity).
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/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce/raw/main/analogy.json)):
163
+ - Accuracy on SAT (full): 0.6122994652406417
164
+ - Accuracy on SAT: 0.6142433234421365
165
+ - Accuracy on BATS: 0.7865480822679266
166
+ - Accuracy on U2: 0.5394736842105263
167
+ - Accuracy on U4: 0.6018518518518519
168
+ - Accuracy on Google: 0.93
169
+ - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce/raw/main/classification.json)):
170
+ - Micro F1 score on BLESS: 0.9174325749585657
171
+ - Micro F1 score on CogALexV: 0.855868544600939
172
+ - Micro F1 score on EVALution: 0.6836403033586133
173
+ - Micro F1 score on K&H+N: 0.9517284551714544
174
+ - Micro F1 score on ROOT09: 0.9019116264493889
175
+ - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce/raw/main/relation_mapping.json)):
176
+ - Accuracy on Relation Mapping: 84.28571428571429
177
+
178
+
179
+ ### Usage
180
+ This model can be used through the [relbert library](https://github.com/asahi417/relbert). Install the library via pip
181
+ ```shell
182
+ pip install relbert
183
+ ```
184
+ and activate model as below.
185
+ ```python
186
+ from relbert import RelBERT
187
+ model = RelBERT("relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce")
188
+ vector = model.get_embedding(['Tokyo', 'Japan']) # shape of (1024, )
189
+ ```
190
+
191
+ ### Training hyperparameters
192
+
193
+ The following hyperparameters were used during training:
194
+ - model: roberta-large
195
+ - max_length: 64
196
+ - mode: average_no_mask
197
+ - data: relbert/semeval2012_relational_similarity
198
+ - template_mode: manual
199
+ - template: Today, I finally discovered the relation between <subj> and <obj> : <obj> is <subj>'s <mask>
200
+ - loss_function: nce_logout
201
+ - temperature_nce_constant: 0.05
202
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
203
+ - epoch: 29
204
+ - batch: 128
205
+ - lr: 5e-06
206
+ - lr_decay: False
207
+ - lr_warmup: 1
208
+ - weight_decay: 0
209
+ - random_seed: 0
210
+ - exclude_relation: None
211
+ - n_sample: 640
212
+ - gradient_accumulation: 8
213
+
214
+ The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-average-no-mask-prompt-b-nce/raw/main/trainer_config.json).
215
+
216
+ ### Reference
217
+ If you use any resource from RelBERT, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
218
+
219
+ ```
220
+
221
+ @inproceedings{ushio-etal-2021-distilling-relation-embeddings,
222
+ title = "{D}istilling {R}elation {E}mbeddings from {P}re-trained {L}anguage {M}odels",
223
+ author = "Ushio, Asahi and
224
+ Schockaert, Steven and
225
+ Camacho-Collados, Jose",
226
+ booktitle = "EMNLP 2021",
227
+ year = "2021",
228
+ address = "Online",
229
+ publisher = "Association for Computational Linguistics",
230
+ }
231
+
232
+ ```