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-b-nce-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: 0.8518253968253968
+  - 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: 0.4679144385026738
+  - 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: 0.4688427299703264
+  - 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: 0.7204002223457476
+  - 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: 0.85
+  - 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: 0.39473684210526316
+  - 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: 0.48842592592592593
+  - 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: 0.9138164833509116
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.9081465241563919
+  - 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: 0.8429577464788731
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6602643050400394
+  - 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: 0.6500541711809318
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6453765088165551
+  - 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: 0.9563886763580719
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8746878565965688
+  - 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: 0.8921968035098715
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8885486080562698
+
+---
+# relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-nce-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-b-nce-0-child-prototypical/raw/main/analogy.json)):
+    - Accuracy on SAT (full): 0.4679144385026738 
+    - Accuracy on SAT: 0.4688427299703264
+    - Accuracy on BATS: 0.7204002223457476
+    - Accuracy on U2: 0.39473684210526316
+    - Accuracy on U4: 0.48842592592592593
+    - Accuracy on Google: 0.85
+- 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-b-nce-0-child-prototypical/raw/main/classification.json)):
+    - Micro F1 score on BLESS: 0.9138164833509116
+    - Micro F1 score on CogALexV: 0.8429577464788731
+    - Micro F1 score on EVALution: 0.6500541711809318
+    - Micro F1 score on K&H+N: 0.9563886763580719
+    - Micro F1 score on ROOT09: 0.8921968035098715
+- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-nce-0-child-prototypical/raw/main/relation_mapping.json)):
+    - Accuracy on Relation Mapping: 0.8518253968253968 
+
+
+### 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-b-nce-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: nce_logout
+ - classification_loss: False
+ - temperature_nce_constant: 0.05
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
+ - epoch: 8
+ - 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-b-nce-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": 0.4688427299703264, "sat/valid": 0.4594594594594595, "u2/test": 0.39473684210526316, "u2/valid": 0.375, "u4/test": 0.48842592592592593, "u4/valid": 0.4583333333333333, "google/test": 0.85, "google/valid": 0.9, "bats/test": 0.7204002223457476, "bats/valid": 0.7487437185929648, "sat_full": 0.4679144385026738}

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": 0.9138164833509116, "test/f1_macro": 0.9081465241563919, "test/f1_micro": 0.9138164833509116, "test/p_macro": 0.9081264819628446, "test/p_micro": 0.9138164833509116, "test/r_macro": 0.9086472654852402, "test/r_micro": 0.9138164833509116}, "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": 0.8429577464788732, "test/f1_macro": 0.6602643050400394, "test/f1_micro": 0.8429577464788731, "test/p_macro": 0.6918108068181256, "test/p_micro": 0.8429577464788732, "test/r_macro": 0.6366330120771996, "test/r_micro": 0.8429577464788732}, "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": 0.6500541711809318, "test/f1_macro": 0.6453765088165551, "test/f1_micro": 0.6500541711809318, "test/p_macro": 0.6566393060903872, "test/p_micro": 0.6500541711809318, "test/r_macro": 0.6420851983369568, "test/r_micro": 0.6500541711809318}, "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": 0.9563886763580719, "test/f1_macro": 0.8746878565965688, "test/f1_micro": 0.9563886763580719, "test/p_macro": 0.8902991066461602, "test/p_micro": 0.9563886763580719, "test/r_macro": 0.8626095096779203, "test/r_micro": 0.9563886763580719}, "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": 0.8921968035098715, "test/f1_macro": 0.8885486080562698, "test/f1_micro": 0.8921968035098715, "test/p_macro": 0.8892467034481256, "test/p_micro": 0.8921968035098715, "test/r_macro": 0.8889553514188181, "test/r_micro": 0.8921968035098715}}

config.json

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5b768fdd00a7290371d10e4b1bf83b823c5ccb7945598c9090901c4bef8039
-size 498649201
+oid sha256:54c3c7196103a651548fe8eed7047db82ad06a41dcf555a9b0e776ae472bb3fe
+size 498652017

relation_mapping.json

@@ -0,0 +1 @@
+{"accuracy": 0.8518253968253968, "prediction": [{"source": ["solar system", "sun", "planet", "mass", "attracts", "revolves", "gravity"], "true": ["atom", "nucleus", "electron", "charge", "attracts", "revolves", "electromagnetism"], "pred": ["nucleus", "electron", "atom", "charge", "attracts", "revolves", "electromagnetism"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.9157185269611691, "similarity_true": 0.9079788403612111}, {"source": ["water", "flows", "pressure", "water tower", "bucket", "filling", "emptying", "hydrodynamics"], "true": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "pred": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "alignment_match": true, "accuracy": 1, "similarity": 0.8502064218862899, "similarity_true": 0.8502064218862899}, {"source": ["waves", "shore", "reflects", "water", "breakwater", "rough", "calm", "crashing"], "true": ["sounds", "wall", "echoes", "air", "insulation", "loud", "quiet", "vibrating"], "pred": ["sounds", "wall", "echoes", "insulation", "air", "loud", "quiet", "vibrating"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.8186605683368684, "similarity_true": 0.8169361406319042}, {"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": 0.894629958517453, "similarity_true": 0.894629958517453}, {"source": ["sound", "low", "high", "echoes", "loud", "quiet", "horn"], "true": ["light", "red", "violet", "reflects", "bright", "dim", "lens"], "pred": ["light", "violet", "red", "reflects", "dim", "bright", "lens"], "alignment_match": false, "accuracy": 0.42857142857142855, "similarity": 0.7987475890031502, "similarity_true": 0.7948486505751576}, {"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": 0.9300468357190312, "similarity_true": 0.9234657990964914}, {"source": ["breeds", "selection", "conformance", "artificial", "popularity", "breeding", "domesticated"], "true": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "pred": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "alignment_match": true, "accuracy": 1, "similarity": 0.8414852272434308, "similarity_true": 0.8414852272434308}, {"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": 0.8590657314279716, "similarity_true": 0.855482634387743}, {"source": ["computer", "processing", "erasing", "write", "read", "memory", "outputs", "inputs", "bug"], "true": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "pred": ["mind", "thinking", "forgetting", "remember", "memorize", "memory", "senses", "muscles", "mistake"], "alignment_match": false, "accuracy": 0.5555555555555556, "similarity": 0.8554078725554092, "similarity_true": 0.853315293018026}, {"source": ["slot machines", "reels", "spinning", "winning", "losing"], "true": ["bacteria", "genes", "mutating", "reproducing", "dying"], "pred": ["bacteria", "genes", "mutating", "reproducing", "dying"], "alignment_match": true, "accuracy": 1, "similarity": 0.7694393850521096, "similarity_true": 0.7694393850521096}, {"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": 0.8307318898839068, "similarity_true": 0.8307318898839068}, {"source": ["buyer", "merchandise", "buying", "selling", "returning", "valuable", "worthless"], "true": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "pred": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "alignment_match": true, "accuracy": 1, "similarity": 0.7779148131797036, "similarity_true": 0.7779148131797036}, {"source": ["foundations", "buildings", "supporting", "solid", "weak", "crack"], "true": ["reasons", "theories", "confirming", "rational", "dubious", "flaw"], "pred": ["theories", "reasons", "confirming", "rational", "dubious", "flaw"], "alignment_match": false, "accuracy": 0.6666666666666666, "similarity": 0.7843681687740658, "similarity_true": 0.7730991581607511}, {"source": ["obstructions", "destination", "route", "traveller", "traveling", "companion", "arriving"], "true": ["difficulties", "goal", "plan", "person", "problem solving", "partner", "succeeding"], "pred": ["difficulties", "goal", "plan", "person", "problem solving", "partner", "succeeding"], "alignment_match": true, "accuracy": 1, "similarity": 0.834965126127087, "similarity_true": 0.834965126127087}, {"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": 0.8263918676540627, "similarity_true": 0.8263918676540627}, {"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": 0.8320528993707552, "similarity_true": 0.8320528993707552}, {"source": ["machine", "working", "turned on", "turned off", "broken", "power", "repair"], "true": ["mind", "thinking", "awake", "asleep", "confused", "intelligence", "therapy"], "pred": ["mind", "thinking", "awake", "asleep", "confused", "intelligence", "therapy"], "alignment_match": true, "accuracy": 1, "similarity": 0.7787864437693168, "similarity_true": 0.7787864437693168}, {"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": 0.7721402088163256, "similarity_true": 0.7667976027040252}, {"source": ["follow", "leader", "path", "follower", "lost", "wanders", "twisted", "straight"], "true": ["understand", "speaker", "argument", "listener", "misunderstood", "digresses", "complicated", "simple"], "pred": ["understand", "speaker", "argument", "listener", "misunderstood", "digresses", "complicated", "simple"], "alignment_match": true, "accuracy": 1, "similarity": 0.8205316109348595, "similarity_true": 0.8205316109348595}, {"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": 0.8097120780372777, "similarity_true": 0.8097120780372777}]}

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/nce_logout.mask.b.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": "Today, I finally discovered the relation between <subj> and <obj> : <obj>  is <subj>'s <mask>", "loss_function": "nce_logout", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 8, "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": 6.010371333456295, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null, "level": "child_prototypical"}