asahi417 commited on
Commit
b3baaa9
1 Parent(s): ded9a1a

model update

Browse files
Files changed (2) hide show
  1. README.md +29 -30
  2. relation_mapping.json +1 -0
README.md CHANGED
@@ -14,7 +14,7 @@ model-index:
14
  metrics:
15
  - name: Accuracy
16
  type: accuracy
17
- value: None
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: None
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: None
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: None
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: None
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: None
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: None
84
  - task:
85
  name: Lexical Relation Classification (BLESS)
86
  type: classification
@@ -91,10 +91,10 @@ model-index:
91
  metrics:
92
  - name: F1
93
  type: f1
94
- value: None
95
  - name: F1 (macro)
96
  type: f1_macro
97
- value: None
98
  - task:
99
  name: Lexical Relation Classification (CogALexV)
100
  type: classification
@@ -105,10 +105,10 @@ model-index:
105
  metrics:
106
  - name: F1
107
  type: f1
108
- value: None
109
  - name: F1 (macro)
110
  type: f1_macro
111
- value: None
112
  - task:
113
  name: Lexical Relation Classification (EVALution)
114
  type: classification
@@ -119,10 +119,10 @@ model-index:
119
  metrics:
120
  - name: F1
121
  type: f1
122
- value: None
123
  - name: F1 (macro)
124
  type: f1_macro
125
- value: None
126
  - task:
127
  name: Lexical Relation Classification (K&H+N)
128
  type: classification
@@ -133,10 +133,10 @@ model-index:
133
  metrics:
134
  - name: F1
135
  type: f1
136
- value: None
137
  - name: F1 (macro)
138
  type: f1_macro
139
- value: None
140
  - task:
141
  name: Lexical Relation Classification (ROOT09)
142
  type: classification
@@ -147,10 +147,10 @@ model-index:
147
  metrics:
148
  - name: F1
149
  type: f1
150
- value: None
151
  - name: F1 (macro)
152
  type: f1_macro
153
- value: None
154
 
155
  ---
156
  # relbert/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1
@@ -160,20 +160,20 @@ RelBERT fine-tuned from [roberta-base](https://huggingface.co/roberta-base) 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/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/analogy.json)):
163
- - Accuracy on SAT (full): None
164
- - Accuracy on SAT: None
165
- - Accuracy on BATS: None
166
- - Accuracy on U2: None
167
- - Accuracy on U4: None
168
- - Accuracy on Google: None
169
  - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/classification.json)):
170
- - Micro F1 score on BLESS: None
171
- - Micro F1 score on CogALexV: None
172
- - Micro F1 score on EVALution: 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/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/relation_mapping.json)):
176
- - Accuracy on Relation Mapping: None
177
 
178
 
179
  ### Usage
@@ -198,7 +198,6 @@ The following hyperparameters were used during training:
198
  - split: train
199
  - split_eval: validation
200
  - template_mode: manual
201
- - template: Today, I finally discovered the relation between <subj> and <obj> : <obj> is <subj>'s <mask>
202
  - loss_function: triplet
203
  - classification_loss: False
204
  - temperature_nce_constant: 0.05
 
14
  metrics:
15
  - name: Accuracy
16
  type: accuracy
17
+ value: 0.7449603174603174
18
  - task:
19
  name: Analogy Questions (SAT full)
20
  type: multiple-choice-qa
 
25
  metrics:
26
  - name: Accuracy
27
  type: accuracy
28
+ value: 0.3502673796791444
29
  - task:
30
  name: Analogy Questions (SAT)
31
  type: multiple-choice-qa
 
36
  metrics:
37
  - name: Accuracy
38
  type: accuracy
39
+ value: 0.3560830860534125
40
  - task:
41
  name: Analogy Questions (BATS)
42
  type: multiple-choice-qa
 
47
  metrics:
48
  - name: Accuracy
49
  type: accuracy
50
+ value: 0.3468593663146192
51
  - task:
52
  name: Analogy Questions (Google)
53
  type: multiple-choice-qa
 
58
  metrics:
59
  - name: Accuracy
60
  type: accuracy
61
+ value: 0.432
62
  - task:
63
  name: Analogy Questions (U2)
64
  type: multiple-choice-qa
 
69
  metrics:
70
  - name: Accuracy
71
  type: accuracy
72
+ value: 0.37719298245614036
73
  - task:
74
  name: Analogy Questions (U4)
75
  type: multiple-choice-qa
 
80
  metrics:
81
  - name: Accuracy
82
  type: accuracy
83
+ value: 0.38425925925925924
84
  - task:
85
  name: Lexical Relation Classification (BLESS)
86
  type: classification
 
91
  metrics:
92
  - name: F1
93
  type: f1
94
+ value: 0.8523429260207925
95
  - name: F1 (macro)
96
  type: f1_macro
97
+ value: 0.8411456349485952
98
  - task:
99
  name: Lexical Relation Classification (CogALexV)
100
  type: classification
 
105
  metrics:
106
  - name: F1
107
  type: f1
108
+ value: 0.8157276995305164
109
  - name: F1 (macro)
110
  type: f1_macro
111
+ value: 0.5982289168562968
112
  - task:
113
  name: Lexical Relation Classification (EVALution)
114
  type: classification
 
119
  metrics:
120
  - name: F1
121
  type: f1
122
+ value: 0.6386782231852655
123
  - name: F1 (macro)
124
  type: f1_macro
125
+ value: 0.6034154846314037
126
  - task:
127
  name: Lexical Relation Classification (K&H+N)
128
  type: classification
 
133
  metrics:
134
  - name: F1
135
  type: f1
136
+ value: 0.95875356472143
137
  - name: F1 (macro)
138
  type: f1_macro
139
+ value: 0.8723815565345302
140
  - task:
141
  name: Lexical Relation Classification (ROOT09)
142
  type: classification
 
147
  metrics:
148
  - name: F1
149
  type: f1
150
+ value: 0.846443121278596
151
  - name: F1 (macro)
152
  type: f1_macro
153
+ value: 0.8238870756074439
154
 
155
  ---
156
  # relbert/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1
 
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-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/analogy.json)):
163
+ - Accuracy on SAT (full): 0.3502673796791444
164
+ - Accuracy on SAT: 0.3560830860534125
165
+ - Accuracy on BATS: 0.3468593663146192
166
+ - Accuracy on U2: 0.37719298245614036
167
+ - Accuracy on U4: 0.38425925925925924
168
+ - Accuracy on Google: 0.432
169
  - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/classification.json)):
170
+ - Micro F1 score on BLESS: 0.8523429260207925
171
+ - Micro F1 score on CogALexV: 0.8157276995305164
172
+ - Micro F1 score on EVALution: 0.6386782231852655
173
+ - Micro F1 score on K&H+N: 0.95875356472143
174
+ - Micro F1 score on ROOT09: 0.846443121278596
175
  - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-b-triplet-1/raw/main/relation_mapping.json)):
176
+ - Accuracy on Relation Mapping: 0.7449603174603174
177
 
178
 
179
  ### Usage
 
198
  - split: train
199
  - split_eval: validation
200
  - template_mode: manual
 
201
  - loss_function: triplet
202
  - classification_loss: False
203
  - temperature_nce_constant: 0.05
relation_mapping.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"accuracy": 0.7449603174603174, "prediction": [{"source": ["solar system", "sun", "planet", "mass", "attracts", "revolves", "gravity"], "true": ["atom", "nucleus", "electron", "charge", "attracts", "revolves", "electromagnetism"], "pred": ["electromagnetism", "atom", "nucleus", "charge", "attracts", "revolves", "electron"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9978007003830888, "similarity_true": 0.9975875796811317}, {"source": ["water", "flows", "pressure", "water tower", "bucket", "filling", "emptying", "hydrodynamics"], "true": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "pred": ["kettle", "transfers", "heat", "temperature", "burner", "cooling", "heating", "thermodynamics"], "alignment_match": false, "accuracy": 0.25, "similarity": 0.9949383115958428, "similarity_true": 0.9947620909443101}, {"source": ["waves", "shore", "reflects", "water", "breakwater", "rough", "calm", "crashing"], "true": ["sounds", "wall", "echoes", "air", "insulation", "loud", "quiet", "vibrating"], "pred": ["sounds", "wall", "echoes", "air", "vibrating", "loud", "quiet", "insulation"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.9968483759183417, "similarity_true": 0.9967963112911737}, {"source": ["combustion", "fire", "fuel", "burning", "hot", "intense", "oxygen", "carbon dioxide"], "true": ["respiration", "animal", "food", "breathing", "living", "vigorous", "oxygen", "carbon dioxide"], "pred": ["respiration", "animal", "food", "breathing", "living", "vigorous", "oxygen", "carbon dioxide"], "alignment_match": true, "accuracy": 1, "similarity": 0.9981043172055925, "similarity_true": 0.9981043172055925}, {"source": ["sound", "low", "high", "echoes", "loud", "quiet", "horn"], "true": ["light", "red", "violet", "reflects", "bright", "dim", "lens"], "pred": ["light", "red", "bright", "reflects", "dim", "violet", "lens"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.9970595350651401, "similarity_true": 0.9969368095324194}, {"source": ["projectile", "trajectory", "earth", "parabolic", "air", "gravity", "attracts"], "true": ["planet", "orbit", "sun", "elliptical", "space", "gravity", "attracts"], "pred": ["sun", "orbit", "planet", "elliptical", "space", "gravity", "attracts"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.9983016817773436, "similarity_true": 0.9983015096314236}, {"source": ["breeds", "selection", "conformance", "artificial", "popularity", "breeding", "domesticated"], "true": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "pred": ["species", "adaptation", "competition", "natural", "fitness", "mating", "wild"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.9964612059134946, "similarity_true": 0.9964290024743016}, {"source": ["ball", "billiards", "speed", "table", "bouncing", "moving", "slow", "fast"], "true": ["molecules", "gas", "temperature", "container", "pressing", "moving", "cold", "hot"], "pred": ["molecules", "gas", "temperature", "container", "pressing", "moving", "cold", "hot"], "alignment_match": true, "accuracy": 1, "similarity": 0.9975199728114164, "similarity_true": 0.9975199728114164}, {"source": ["computer", "processing", "erasing", "write", "read", "memory", "outputs", "inputs", "bug"], "true": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "pred": ["mind", "thinking", "memorize", "forgetting", "remember", "memory", "muscles", "senses", "mistake"], "alignment_match": false, "accuracy": 0.7777777777777778, "similarity": 0.9965320817380313, "similarity_true": 0.9964552173386212}, {"source": ["slot machines", "reels", "spinning", "winning", "losing"], "true": ["bacteria", "genes", "mutating", "reproducing", "dying"], "pred": ["mutating", "genes", "bacteria", "reproducing", "dying"], "alignment_match": false, "accuracy": 0.6, "similarity": 0.9945571008641886, "similarity_true": 0.9945563331831058}, {"source": ["war", "soldier", "destroy", "fighting", "defeat", "attacks", "weapon"], "true": ["argument", "debater", "refute", "arguing", "acceptance", "criticizes", "logic"], "pred": ["argument", "debater", "refute", "arguing", "acceptance", "criticizes", "logic"], "alignment_match": true, "accuracy": 1, "similarity": 0.9945850218735248, "similarity_true": 0.9945850218735248}, {"source": ["buyer", "merchandise", "buying", "selling", "returning", "valuable", "worthless"], "true": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "pred": ["believer", "belief", "rejecting", "advocating", "accepting", "true", "false"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.9957467710289237, "similarity_true": 0.995739333833242}, {"source": ["foundations", "buildings", "supporting", "solid", "weak", "crack"], "true": ["reasons", "theories", "confirming", "rational", "dubious", "flaw"], "pred": ["reasons", "theories", "confirming", "rational", "dubious", "flaw"], "alignment_match": true, "accuracy": 1, "similarity": 0.996877981935695, "similarity_true": 0.996877981935695}, {"source": ["obstructions", "destination", "route", "traveller", "traveling", "companion", "arriving"], "true": ["difficulties", "goal", "plan", "person", "problem solving", "partner", "succeeding"], "pred": ["problem solving", "goal", "plan", "person", "difficulties", "partner", "succeeding"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.9947483897730063, "similarity_true": 0.9947357996316091}, {"source": ["money", "allocate", "budget", "effective", "cheap", "expansive"], "true": ["time", "invest", "schedule", "efficient", "quick", "slow"], "pred": ["time", "invest", "schedule", "efficient", "quick", "slow"], "alignment_match": true, "accuracy": 1, "similarity": 0.997373157147748, "similarity_true": 0.997373157147748}, {"source": ["seeds", "planted", "fruitful", "fruit", "grow", "wither", "blossom"], "true": ["ideas", "inspired", "productive", "product", "develop", "fail", "succeed"], "pred": ["ideas", "inspired", "productive", "product", "develop", "fail", "succeed"], "alignment_match": true, "accuracy": 1, "similarity": 0.9964193622914028, "similarity_true": 0.9964193622914028}, {"source": ["machine", "working", "turned on", "turned off", "broken", "power", "repair"], "true": ["mind", "thinking", "awake", "asleep", "confused", "intelligence", "therapy"], "pred": ["mind", "asleep", "awake", "thinking", "confused", "intelligence", "therapy"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.9956977474695079, "similarity_true": 0.9956832817196968}, {"source": ["object", "hold", "weight", "heavy", "light"], "true": ["idea", "understand", "analyze", "important", "trivial"], "pred": ["idea", "analyze", "understand", "trivial", "important"], "alignment_match": false, "accuracy": 0.2, "similarity": 0.9954065370534377, "similarity_true": 0.9947540103505097}, {"source": ["follow", "leader", "path", "follower", "lost", "wanders", "twisted", "straight"], "true": ["understand", "speaker", "argument", "listener", "misunderstood", "digresses", "complicated", "simple"], "pred": ["understand", "speaker", "argument", "listener", "complicated", "digresses", "misunderstood", "simple"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.9958884956064967, "similarity_true": 0.9958305143006762}, {"source": ["seeing", "light", "illuminating", "darkness", "view", "hidden"], "true": ["understanding", "knowledge", "explaining", "confusion", "interpretation", "secret"], "pred": ["understanding", "knowledge", "explaining", "confusion", "interpretation", "secret"], "alignment_match": true, "accuracy": 1, "similarity": 0.9966974449211523, "similarity_true": 0.9966974449211523}]}