model update

README.md

@@ -0,0 +1,236 @@
+---
+datasets:
+- relbert/semeval2012_relational_similarity_v6
+model-index:
+- name: relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical
+  results:
+  - task:
+      name: Relation Mapping
+      type: sorting-task
+    dataset:
+      name: Relation Mapping
+      args: relbert/relation_mapping
+      type: relation-mapping
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.38442460317460314
+  - task:
+      name: Analogy Questions (SAT full)
+      type: multiple-choice-qa
+    dataset:
+      name: SAT full
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.23529411764705882
+  - task:
+      name: Analogy Questions (SAT)
+      type: multiple-choice-qa
+    dataset:
+      name: SAT
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.2314540059347181
+  - task:
+      name: Analogy Questions (BATS)
+      type: multiple-choice-qa
+    dataset:
+      name: BATS
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.3229571984435798
+  - task:
+      name: Analogy Questions (Google)
+      type: multiple-choice-qa
+    dataset:
+      name: Google
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.384
+  - task:
+      name: Analogy Questions (U2)
+      type: multiple-choice-qa
+    dataset:
+      name: U2
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.3157894736842105
+  - task:
+      name: Analogy Questions (U4)
+      type: multiple-choice-qa
+    dataset:
+      name: U4
+      args: relbert/analogy_questions
+      type: analogy-questions
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.2847222222222222
+  - task:
+      name: Lexical Relation Classification (BLESS)
+      type: classification
+    dataset:
+      name: BLESS
+      args: relbert/lexical_relation_classification
+      type: relation-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6522525237306012
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.616560269476982
+  - task:
+      name: Lexical Relation Classification (CogALexV)
+      type: classification
+    dataset:
+      name: CogALexV
+      args: relbert/lexical_relation_classification
+      type: relation-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.7183098591549296
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.16833503884438658
+  - task:
+      name: Lexical Relation Classification (EVALution)
+      type: classification
+    dataset:
+      name: BLESS
+      args: relbert/lexical_relation_classification
+      type: relation-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.42632719393282775
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.28678399596569476
+  - task:
+      name: Lexical Relation Classification (K&H+N)
+      type: classification
+    dataset:
+      name: K&H+N
+      args: relbert/lexical_relation_classification
+      type: relation-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.8141475968560896
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6286243048790003
+  - task:
+      name: Lexical Relation Classification (ROOT09)
+      type: classification
+    dataset:
+      name: ROOT09
+      args: relbert/lexical_relation_classification
+      type: relation-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.6552804763397054
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.5562839421136045
+
+---
+# relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical
+
+RelBERT fine-tuned from [roberta-base](https://huggingface.co/roberta-base) on  
+[relbert/semeval2012_relational_similarity_v6](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity_v6).
+Fine-tuning is done via [RelBERT](https://github.com/asahi417/relbert) library (see the repository for more detail).
+It achieves the following results on the relation understanding tasks:
+- Analogy Question ([dataset](https://huggingface.co/datasets/relbert/analogy_questions), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical/raw/main/analogy.json)):
+    - Accuracy on SAT (full): 0.23529411764705882 
+    - Accuracy on SAT: 0.2314540059347181
+    - Accuracy on BATS: 0.3229571984435798
+    - Accuracy on U2: 0.3157894736842105
+    - Accuracy on U4: 0.2847222222222222
+    - Accuracy on Google: 0.384
+- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical/raw/main/classification.json)):
+    - Micro F1 score on BLESS: 0.6522525237306012
+    - Micro F1 score on CogALexV: 0.7183098591549296
+    - Micro F1 score on EVALution: 0.42632719393282775
+    - Micro F1 score on K&H+N: 0.8141475968560896
+    - Micro F1 score on ROOT09: 0.6552804763397054
+- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical/raw/main/relation_mapping.json)):
+    - Accuracy on Relation Mapping: 0.38442460317460314 
+
+
+### Usage
+This model can be used through the [relbert library](https://github.com/asahi417/relbert). Install the library via pip   
+```shell
+pip install relbert
+```
+and activate model as below.
+```python
+from relbert import RelBERT
+model = RelBERT("relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical")
+vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (1024, )
+```
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+ - model: roberta-base
+ - max_length: 64
+ - mode: mask
+ - data: relbert/semeval2012_relational_similarity_v6
+ - split: train
+ - split_eval: validation
+ - template_mode: manual
+ - loss_function: triplet
+ - classification_loss: False
+ - temperature_nce_constant: 0.05
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
+ - epoch: 2
+ - batch: 128
+ - lr: 5e-06
+ - lr_decay: False
+ - lr_warmup: 1
+ - weight_decay: 0
+ - random_seed: 0
+ - exclude_relation: None
+ - n_sample: 320
+ - gradient_accumulation: 8
+ - relation_level: None
+ - data_level: child_prototypical
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-e-triplet-0-child-prototypical/raw/main/trainer_config.json).
+
+### Reference
+If you use any resource from RelBERT, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
+
+```
+
+@inproceedings{ushio-etal-2021-distilling-relation-embeddings,
+    title = "{D}istilling {R}elation {E}mbeddings from {P}re-trained {L}anguage {M}odels",
+    author = "Ushio, Asahi  and
+      Schockaert, Steven  and
+      Camacho-Collados, Jose",
+    booktitle = "EMNLP 2021",
+    year = "2021",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+}
+
+```

analogy.json

@@ -0,0 +1 @@
+{"distance_function": "cosine_similarity", "sat/test": 0.2314540059347181, "sat/valid": 0.2702702702702703, "u2/test": 0.3157894736842105, "u2/valid": 0.2916666666666667, "u4/test": 0.2847222222222222, "u4/valid": 0.2708333333333333, "google/test": 0.384, "google/valid": 0.46, "bats/test": 0.3229571984435798, "bats/valid": 0.2864321608040201, "sat_full": 0.23529411764705882}

classification.json

@@ -0,0 +1 @@
+{"lexical_relation_classification/BLESS": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.6522525237306012, "test/f1_macro": 0.616560269476982, "test/f1_micro": 0.6522525237306012, "test/p_macro": 0.6327396676541002, "test/p_micro": 0.6522525237306012, "test/r_macro": 0.6389545655489762, "test/r_micro": 0.6522525237306012}, "lexical_relation_classification/CogALexV": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.7183098591549296, "test/f1_macro": 0.16833503884438658, "test/f1_micro": 0.7183098591549296, "test/p_macro": 0.34368248003757634, "test/p_micro": 0.7183098591549296, "test/r_macro": 0.20055555555555554, "test/r_micro": 0.7183098591549296}, "lexical_relation_classification/EVALution": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.42632719393282775, "test/f1_macro": 0.28678399596569476, "test/f1_micro": 0.42632719393282775, "test/p_macro": 0.35191649016357834, "test/p_micro": 0.42632719393282775, "test/r_macro": 0.3066647799615754, "test/r_micro": 0.42632719393282775}, "lexical_relation_classification/K&H+N": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.8141475968560896, "test/f1_macro": 0.6286243048790003, "test/f1_micro": 0.8141475968560896, "test/p_macro": 0.7020667520537744, "test/p_micro": 0.8141475968560896, "test/r_macro": 0.61205810359152, "test/r_micro": 0.8141475968560896}, "lexical_relation_classification/ROOT09": {"classifier_config": {"activation": "relu", "alpha": 0.0001, "batch_size": "auto", "beta_1": 0.9, "beta_2": 0.999, "early_stopping": false, "epsilon": 1e-08, "hidden_layer_sizes": [100], "learning_rate": "constant", "learning_rate_init": 0.001, "max_fun": 15000, "max_iter": 200, "momentum": 0.9, "n_iter_no_change": 10, "nesterovs_momentum": true, "power_t": 0.5, "random_state": 0, "shuffle": true, "solver": "adam", "tol": 0.0001, "validation_fraction": 0.1, "verbose": false, "warm_start": false}, "test/accuracy": 0.6552804763397054, "test/f1_macro": 0.5562839421136045, "test/f1_micro": 0.6552804763397054, "test/p_macro": 0.6480151680720655, "test/p_micro": 0.6552804763397054, "test/r_macro": 0.6060111247216715, "test/r_micro": 0.6552804763397054}}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "relbert_output/models/semeval2012-v6-child_prototypical/triplet.mask.e.0",
+  "_name_or_path": "roberta-base",
   "architectures": [
     "RobertaModel"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6c1c203ebe45d119b927374fbd0463e8359eab5e41af49897ca29ee317ccf3
-size 498649201
+oid sha256:154713fa137cb32dd874bece3026ee1107c531b7e2c8a76e8e0f771f991bda3d
+size 498652017

relation_mapping.json

@@ -0,0 +1 @@
+{"accuracy": 0.38442460317460314, "prediction": [{"source": ["solar system", "sun", "planet", "mass", "attracts", "revolves", "gravity"], "true": ["atom", "nucleus", "electron", "charge", "attracts", "revolves", "electromagnetism"], "pred": ["electromagnetism", "charge", "electron", "nucleus", "attracts", "revolves", "atom"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9998986814135402, "similarity_true": 0.9997957960954895}, {"source": ["water", "flows", "pressure", "water tower", "bucket", "filling", "emptying", "hydrodynamics"], "true": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "pred": ["kettle", "cooling", "burner", "temperature", "transfers", "heating", "heat", "thermodynamics"], "alignment_match": false, "accuracy": 0.25, "similarity": 0.9998519345291734, "similarity_true": 0.9998062446897042}, {"source": ["waves", "shore", "reflects", "water", "breakwater", "rough", "calm", "crashing"], "true": ["sounds", "wall", "echoes", "air", "insulation", "loud", "quiet", "vibrating"], "pred": ["echoes", "quiet", "sounds", "air", "vibrating", "loud", "wall", "insulation"], "alignment_match": false, "accuracy": 0.25, "similarity": 0.9998885003248263, "similarity_true": 0.9997877377317981}, {"source": ["combustion", "fire", "fuel", "burning", "hot", "intense", "oxygen", "carbon dioxide"], "true": ["respiration", "animal", "food", "breathing", "living", "vigorous", "oxygen", "carbon dioxide"], "pred": ["vigorous", "animal", "food", "respiration", "breathing", "living", "oxygen", "carbon dioxide"], "alignment_match": false, "accuracy": 0.5, "similarity": 0.9999402877737723, "similarity_true": 0.9999207848671514}, {"source": ["sound", "low", "high", "echoes", "loud", "quiet", "horn"], "true": ["light", "red", "violet", "reflects", "bright", "dim", "lens"], "pred": ["dim", "red", "bright", "reflects", "violet", "light", "lens"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9998792088171351, "similarity_true": 0.9998470043107288}, {"source": ["projectile", "trajectory", "earth", "parabolic", "air", "gravity", "attracts"], "true": ["planet", "orbit", "sun", "elliptical", "space", "gravity", "attracts"], "pred": ["orbit", "space", "planet", "elliptical", "sun", "gravity", "attracts"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9999535285107376, "similarity_true": 0.9999353786494936}, {"source": ["breeds", "selection", "conformance", "artificial", "popularity", "breeding", "domesticated"], "true": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "pred": ["species", "adaptation", "mating", "natural", "competition", "fitness", "wild"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9999052091684724, "similarity_true": 0.9998966181588057}, {"source": ["ball", "billiards", "speed", "table", "bouncing", "moving", "slow", "fast"], "true": ["molecules", "gas", "temperature", "container", "pressing", "moving", "cold", "hot"], "pred": ["gas", "molecules", "temperature", "container", "pressing", "moving", "cold", "hot"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.999871883343893, "similarity_true": 0.999866935281706}, {"source": ["computer", "processing", "erasing", "write", "read", "memory", "outputs", "inputs", "bug"], "true": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "pred": ["mistake", "muscles", "thinking", "remember", "memorize", "memory", "senses", "forgetting", "mind"], "alignment_match": false, "accuracy": 0.1111111111111111, "similarity": 0.9998649963141523, "similarity_true": 0.9998444501292136}, {"source": ["slot machines", "reels", "spinning", "winning", "losing"], "true": ["bacteria", "genes", "mutating", "reproducing", "dying"], "pred": ["genes", "mutating", "bacteria", "reproducing", "dying"], "alignment_match": false, "accuracy": 0.4, "similarity": 0.9998052683496003, "similarity_true": 0.9997359221067951}, {"source": ["war", "soldier", "destroy", "fighting", "defeat", "attacks", "weapon"], "true": ["argument", "debater", "refute", "arguing", "acceptance", "criticizes", "logic"], "pred": ["logic", "debater", "criticizes", "arguing", "argument", "refute", "acceptance"], "alignment_match": false, "accuracy": 0.2857142857142857, "similarity": 0.9998387431318707, "similarity_true": 0.9998022495196359}, {"source": ["buyer", "merchandise", "buying", "selling", "returning", "valuable", "worthless"], "true": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "pred": ["accepting", "believer", "belief", "rejecting", "true", "advocating", "false"], "alignment_match": false, "accuracy": 0.14285714285714285, "similarity": 0.9998433640713058, "similarity_true": 0.9997948803161422}, {"source": ["foundations", "buildings", "supporting", "solid", "weak", "crack"], "true": ["reasons", "theories", "confirming", "rational", "dubious", "flaw"], "pred": ["dubious", "theories", "reasons", "confirming", "flaw", "rational"], "alignment_match": false, "accuracy": 0.16666666666666666, "similarity": 0.9998684254009585, "similarity_true": 0.9998656516970459}, {"source": ["obstructions", "destination", "route", "traveller", "traveling", "companion", "arriving"], "true": ["difficulties", "goal", "plan", "person", "problem solving", "partner", "succeeding"], "pred": ["problem solving", "partner", "goal", "difficulties", "plan", "person", "succeeding"], "alignment_match": false, "accuracy": 0.14285714285714285, "similarity": 0.9998998083983347, "similarity_true": 0.9998575675062743}, {"source": ["money", "allocate", "budget", "effective", "cheap", "expansive"], "true": ["time", "invest", "schedule", "efficient", "quick", "slow"], "pred": ["time", "invest", "schedule", "quick", "slow", "efficient"], "alignment_match": false, "accuracy": 0.5, "similarity": 0.9999222406788741, "similarity_true": 0.9999181486897804}, {"source": ["seeds", "planted", "fruitful", "fruit", "grow", "wither", "blossom"], "true": ["ideas", "inspired", "productive", "product", "develop", "fail", "succeed"], "pred": ["succeed", "ideas", "productive", "product", "develop", "fail", "inspired"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.9998159316449768, "similarity_true": 0.9997895832756956}, {"source": ["machine", "working", "turned on", "turned off", "broken", "power", "repair"], "true": ["mind", "thinking", "awake", "asleep", "confused", "intelligence", "therapy"], "pred": ["intelligence", "thinking", "therapy", "asleep", "confused", "mind", "awake"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.9998155176793945, "similarity_true": 0.9997618964902606}, {"source": ["object", "hold", "weight", "heavy", "light"], "true": ["idea", "understand", "analyze", "important", "trivial"], "pred": ["idea", "analyze", "understand", "important", "trivial"], "alignment_match": false, "accuracy": 0.6, "similarity": 0.9997860629398051, "similarity_true": 0.999775265453976}, {"source": ["follow", "leader", "path", "follower", "lost", "wanders", "twisted", "straight"], "true": ["understand", "speaker", "argument", "listener", "misunderstood", "digresses", "complicated", "simple"], "pred": ["simple", "listener", "understand", "speaker", "misunderstood", "digresses", "complicated", "argument"], "alignment_match": false, "accuracy": 0.375, "similarity": 0.9998561435912088, "similarity_true": 0.9998356567540803}, {"source": ["seeing", "light", "illuminating", "darkness", "view", "hidden"], "true": ["understanding", "knowledge", "explaining", "confusion", "interpretation", "secret"], "pred": ["understanding", "confusion", "explaining", "secret", "interpretation", "knowledge"], "alignment_match": false, "accuracy": 0.5, "similarity": 0.9998257714200894, "similarity_true": 0.9997823601002886}]}

tokenizer_config.json

@@ -6,7 +6,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "relbert_output/models/semeval2012-v6-child_prototypical/triplet.mask.e.0",
+  "name_or_path": "roberta-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "special_tokens_map_file": null,

trainer_config.json

@@ -0,0 +1 @@
+{"model": "roberta-base", "max_length": 64, "mode": "mask", "data": "relbert/semeval2012_relational_similarity_v6", "split": "train", "split_eval": "validation", "template_mode": "manual", "template": "I wasn\u2019t aware of this relationship, but I just read in the encyclopedia that <obj>  is <subj>\u2019s <mask>", "loss_function": "triplet", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 2, "batch": 128, "lr": 5e-06, "lr_decay": false, "lr_warmup": 1, "weight_decay": 0, "random_seed": 0, "exclude_relation": null, "n_sample": 320, "gradient_accumulation": 8, "relation_level": null, "data_level": "child_prototypical"}

validation_loss.json

@@ -0,0 +1 @@
+{"split": "validation", "loss": 0.9499067174906018, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null, "level": "child_prototypical"}