model update

README.md

@@ -0,0 +1,235 @@
+---
+datasets:
+- relbert/semeval2012_relational_similarity_v6
+model-index:
+- name: relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-loob-0
+  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: 0.6438492063492064
+  - 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: 0.32887700534759357
+  - 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: 0.3264094955489614
+  - 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: 0.5302946081156198
+  - 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: 0.648
+  - 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: 0.3201754385964912
+  - 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: 0.36574074074074076
+  - 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: 0.877655567274371
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8691271164987491
+  - 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: 0.7129107981220657
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.4196917803483246
+  - 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: 0.5368364030335862
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.5188634387372184
+  - 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: 0.9531195659734298
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8766279141586715
+  - 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: 0.8031964901284864
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8003449544921196
+
+---
+# relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-loob-0
+
+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-average-prompt-c-loob-0/raw/main/analogy.json)):
+    - Accuracy on SAT (full): 0.32887700534759357 
+    - Accuracy on SAT: 0.3264094955489614
+    - Accuracy on BATS: 0.5302946081156198
+    - Accuracy on U2: 0.3201754385964912
+    - Accuracy on U4: 0.36574074074074076
+    - Accuracy on Google: 0.648
+- 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-c-loob-0/raw/main/classification.json)):
+    - Micro F1 score on BLESS: 0.877655567274371
+    - Micro F1 score on CogALexV: 0.7129107981220657
+    - Micro F1 score on EVALution: 0.5368364030335862
+    - Micro F1 score on K&H+N: 0.9531195659734298
+    - Micro F1 score on ROOT09: 0.8031964901284864
+- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-loob-0/raw/main/relation_mapping.json)):
+    - Accuracy on Relation Mapping: 0.6438492063492064 
+
+
+### 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-average-prompt-c-loob-0")
+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: average
+ - data: relbert/semeval2012_relational_similarity_v6
+ - split: train
+ - split_eval: validation
+ - template_mode: manual
+ - loss_function: info_loob
+ - classification_loss: False
+ - temperature_nce_constant: 0.05
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
+ - epoch: 10
+ - 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
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-loob-0/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": 0.3264094955489614, "sat/valid": 0.35135135135135137, "u2/test": 0.3201754385964912, "u2/valid": 0.2916666666666667, "u4/test": 0.36574074074074076, "u4/valid": 0.375, "google/test": 0.648, "google/valid": 0.68, "bats/test": 0.5302946081156198, "bats/valid": 0.5979899497487438, "sat_full": 0.32887700534759357}

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": 0.877655567274371, "test/f1_macro": 0.8691271164987491, "test/f1_micro": 0.877655567274371, "test/p_macro": 0.8702519502264461, "test/p_micro": 0.877655567274371, "test/r_macro": 0.8683594985863752, "test/r_micro": 0.877655567274371}, "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": 0.7129107981220657, "test/f1_macro": 0.4196917803483246, "test/f1_micro": 0.7129107981220657, "test/p_macro": 0.4454147273209427, "test/p_micro": 0.7129107981220657, "test/r_macro": 0.40126030693272546, "test/r_micro": 0.7129107981220657}, "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": 0.5368364030335862, "test/f1_macro": 0.5188634387372184, "test/f1_micro": 0.5368364030335862, "test/p_macro": 0.5315946062326986, "test/p_micro": 0.5368364030335862, "test/r_macro": 0.5116213650204663, "test/r_micro": 0.5368364030335862}, "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": 0.9531195659734298, "test/f1_macro": 0.8766279141586715, "test/f1_micro": 0.9531195659734298, "test/p_macro": 0.8962210066132437, "test/p_micro": 0.9531195659734298, "test/r_macro": 0.8596966206120572, "test/r_micro": 0.9531195659734298}, "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": 0.8031964901284864, "test/f1_macro": 0.8003449544921196, "test/f1_micro": 0.8031964901284864, "test/p_macro": 0.7985073234275869, "test/p_micro": 0.8031964901284864, "test/r_macro": 0.8023155275351975, "test/r_micro": 0.8031964901284864}}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "relbert_output/models/semeval2012-v6.c.info_loob.average.roberta-base.0.000005.8.0.05.320.0/best_model",
+  "_name_or_path": "roberta-base",
   "architectures": [
     "RobertaModel"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad2a5db8f019ca481338e026e4f104c72aa56709850aa1172171333f15ece74
-size 498649201
+oid sha256:15876d8ca1c809793098b21a2fd1aa55d75820e2ae79d51241ce72de0a5fe507
+size 498652017

relation_mapping.json

@@ -0,0 +1 @@
+{"accuracy": 0.6438492063492064, "prediction": [{"source": ["solar system", "sun", "planet", "mass", "attracts", "revolves", "gravity"], "true": ["atom", "nucleus", "electron", "charge", "attracts", "revolves", "electromagnetism"], "pred": ["electromagnetism", "electron", "nucleus", "atom", "attracts", "revolves", "charge"], "alignment_match": false, "accuracy": 0.2857142857142857, "similarity": 0.7724826312481731, "similarity_true": 0.7232682454577108}, {"source": ["water", "flows", "pressure", "water tower", "bucket", "filling", "emptying", "hydrodynamics"], "true": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "pred": ["heat", "burner", "temperature", "transfers", "kettle", "heating", "cooling", "thermodynamics"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.300724207844675, "similarity_true": 0.29664231307175437}, {"source": ["waves", "shore", "reflects", "water", "breakwater", "rough", "calm", "crashing"], "true": ["sounds", "wall", "echoes", "air", "insulation", "loud", "quiet", "vibrating"], "pred": ["sounds", "wall", "echoes", "air", "insulation", "loud", "quiet", "vibrating"], "alignment_match": true, "accuracy": 1, "similarity": 0.40698160439182474, "similarity_true": 0.40698160439182474}, {"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": 0.6133862590739939, "similarity_true": 0.6133862590739939}, {"source": ["sound", "low", "high", "echoes", "loud", "quiet", "horn"], "true": ["light", "red", "violet", "reflects", "bright", "dim", "lens"], "pred": ["light", "red", "reflects", "violet", "bright", "dim", "lens"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.7871932597260537, "similarity_true": 0.7735238397507866}, {"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": 0.8705342989734675, "similarity_true": 0.8640845424498501}, {"source": ["breeds", "selection", "conformance", "artificial", "popularity", "breeding", "domesticated"], "true": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "pred": ["species", "adaptation", "fitness", "natural", "competition", "mating", "wild"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.6991709253652926, "similarity_true": 0.6731746800680759}, {"source": ["ball", "billiards", "speed", "table", "bouncing", "moving", "slow", "fast"], "true": ["molecules", "gas", "temperature", "container", "pressing", "moving", "cold", "hot"], "pred": ["molecules", "gas", "temperature", "container", "cold", "moving", "pressing", "hot"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.7845157744442195, "similarity_true": 0.7808282631426937}, {"source": ["computer", "processing", "erasing", "write", "read", "memory", "outputs", "inputs", "bug"], "true": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "pred": ["senses", "forgetting", "thinking", "remember", "muscles", "memory", "mind", "memorize", "mistake"], "alignment_match": false, "accuracy": 0.2222222222222222, "similarity": 0.7494422063048711, "similarity_true": 0.7353060077015228}, {"source": ["slot machines", "reels", "spinning", "winning", "losing"], "true": ["bacteria", "genes", "mutating", "reproducing", "dying"], "pred": ["bacteria", "genes", "reproducing", "mutating", "dying"], "alignment_match": false, "accuracy": 0.6, "similarity": 0.28346165131729056, "similarity_true": 0.24754729720333474}, {"source": ["war", "soldier", "destroy", "fighting", "defeat", "attacks", "weapon"], "true": ["argument", "debater", "refute", "arguing", "acceptance", "criticizes", "logic"], "pred": ["argument", "debater", "refute", "arguing", "acceptance", "logic", "criticizes"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.31032564051218475, "similarity_true": 0.2899659783334826}, {"source": ["buyer", "merchandise", "buying", "selling", "returning", "valuable", "worthless"], "true": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "pred": ["believer", "belief", "accepting", "false", "rejecting", "true", "advocating"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.29282796592124677, "similarity_true": 0.27978962955554176}, {"source": ["foundations", "buildings", "supporting", "solid", "weak", "crack"], "true": ["reasons", "theories", "confirming", "rational", "dubious", "flaw"], "pred": ["theories", "rational", "confirming", "reasons", "flaw", "dubious"], "alignment_match": false, "accuracy": 0.16666666666666666, "similarity": 0.22027388310834467, "similarity_true": 0.18823163323084224}, {"source": ["obstructions", "destination", "route", "traveller", "traveling", "companion", "arriving"], "true": ["difficulties", "goal", "plan", "person", "problem solving", "partner", "succeeding"], "pred": ["difficulties", "person", "plan", "goal", "problem solving", "partner", "succeeding"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.3605133764416722, "similarity_true": 0.3603943168037333}, {"source": ["money", "allocate", "budget", "effective", "cheap", "expansive"], "true": ["time", "invest", "schedule", "efficient", "quick", "slow"], "pred": ["invest", "time", "schedule", "efficient", "quick", "slow"], "alignment_match": false, "accuracy": 0.6666666666666666, "similarity": 0.27929782259615443, "similarity_true": 0.27611494014153914}, {"source": ["seeds", "planted", "fruitful", "fruit", "grow", "wither", "blossom"], "true": ["ideas", "inspired", "productive", "product", "develop", "fail", "succeed"], "pred": ["ideas", "succeed", "productive", "inspired", "develop", "fail", "product"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.29245608410932267, "similarity_true": 0.27841258349247516}, {"source": ["machine", "working", "turned on", "turned off", "broken", "power", "repair"], "true": ["mind", "thinking", "awake", "asleep", "confused", "intelligence", "therapy"], "pred": ["asleep", "thinking", "mind", "awake", "confused", "intelligence", "therapy"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.2920938882199935, "similarity_true": 0.28394532848544246}, {"source": ["object", "hold", "weight", "heavy", "light"], "true": ["idea", "understand", "analyze", "important", "trivial"], "pred": ["trivial", "understand", "idea", "important", "analyze"], "alignment_match": false, "accuracy": 0.4, "similarity": 0.271852394337335, "similarity_true": 0.26428489274812306}, {"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": 0.35785509296761076, "similarity_true": 0.34589510020522535}, {"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": 0.40748961347131474, "similarity_true": 0.40748961347131474}]}

tokenizer_config.json

@@ -6,7 +6,7 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "relbert_output/models/semeval2012-v6.c.info_loob.average.roberta-base.0.000005.8.0.05.320.0/best_model",
+  "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": "average", "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> : <mask>", "loss_function": "info_loob", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 10, "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}

validation_loss.json

@@ -0,0 +1 @@
+{"split": "validation", "loss": -17.238929681799483, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null}