model update

README.md

@@ -0,0 +1,236 @@
+---
+datasets:
+- relbert/semeval2012_relational_similarity_v6
+model-index:
+- name: relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-nce-1-child
+  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: 0.8001190476190476
+  - 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: 0.4385026737967914
+  - 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: 0.4362017804154303
+  - 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: 0.5786548082267927
+  - 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: 0.802
+  - 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: 0.41228070175438597
+  - 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: 0.4074074074074074
+  - 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: 0.9026668675606448
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.894134460103921
+  - 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: 0.8044600938967136
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.5658272058955415
+  - 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: 0.6343445287107259
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.6053012278166984
+  - 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: 0.9589622313417264
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8820483966915638
+  - 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: 0.8824819805703541
+    - name: F1 (macro)
+      type: f1_macro
+      value: 0.8778053649821325
+
+---
+# relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-nce-1-child
+
+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-nce-1-child/raw/main/analogy.json)):
+    - Accuracy on SAT (full): 0.4385026737967914 
+    - Accuracy on SAT: 0.4362017804154303
+    - Accuracy on BATS: 0.5786548082267927
+    - Accuracy on U2: 0.41228070175438597
+    - Accuracy on U4: 0.4074074074074074
+    - Accuracy on Google: 0.802
+- 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-nce-1-child/raw/main/classification.json)):
+    - Micro F1 score on BLESS: 0.9026668675606448
+    - Micro F1 score on CogALexV: 0.8044600938967136
+    - Micro F1 score on EVALution: 0.6343445287107259
+    - Micro F1 score on K&H+N: 0.9589622313417264
+    - Micro F1 score on ROOT09: 0.8824819805703541
+- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-nce-1-child/raw/main/relation_mapping.json)):
+    - Accuracy on Relation Mapping: 0.8001190476190476 
+
+
+### 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-nce-1-child")
+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: nce_logout
+ - classification_loss: False
+ - temperature_nce_constant: 0.05
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
+ - epoch: 5
+ - batch: 128
+ - lr: 5e-06
+ - lr_decay: False
+ - lr_warmup: 1
+ - weight_decay: 0
+ - random_seed: 1
+ - exclude_relation: None
+ - n_sample: 320
+ - gradient_accumulation: 8
+ - relation_level: None
+ - data_level: child
+
+The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-average-prompt-c-nce-1-child/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": 0.4362017804154303, "sat/valid": 0.4594594594594595, "u2/test": 0.41228070175438597, "u2/valid": 0.4166666666666667, "u4/test": 0.4074074074074074, "u4/valid": 0.3958333333333333, "google/test": 0.802, "google/valid": 0.84, "bats/test": 0.5786548082267927, "bats/valid": 0.5527638190954773, "sat_full": 0.4385026737967914}

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": 0.9026668675606448, "test/f1_macro": 0.894134460103921, "test/f1_micro": 0.9026668675606448, "test/p_macro": 0.892588409876728, "test/p_micro": 0.9026668675606448, "test/r_macro": 0.8964480044828029, "test/r_micro": 0.9026668675606448}, "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": 0.8044600938967136, "test/f1_macro": 0.5658272058955415, "test/f1_micro": 0.8044600938967136, "test/p_macro": 0.6174598416344621, "test/p_micro": 0.8044600938967136, "test/r_macro": 0.5302328559317095, "test/r_micro": 0.8044600938967136}, "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": 0.6343445287107259, "test/f1_macro": 0.6053012278166984, "test/f1_micro": 0.6343445287107259, "test/p_macro": 0.6223254319659148, "test/p_micro": 0.6343445287107259, "test/r_macro": 0.5967483205756926, "test/r_micro": 0.6343445287107259}, "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": 0.9589622313417264, "test/f1_macro": 0.8820483966915638, "test/f1_micro": 0.9589622313417264, "test/p_macro": 0.8890767331056941, "test/p_micro": 0.9589622313417264, "test/r_macro": 0.8753427090914881, "test/r_micro": 0.9589622313417264}, "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": 0.8824819805703541, "test/f1_macro": 0.8778053649821325, "test/f1_micro": 0.8824819805703541, "test/p_macro": 0.883074485741249, "test/p_micro": 0.8824819805703541, "test/r_macro": 0.8744216188970667, "test/r_micro": 0.8824819805703541}}

config.json

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cef8a3734fe181e868bbcd39aac33a9ad5ff5e51350d76bf50a8c285cc20394
-size 498649201
+oid sha256:5255f21a611580ae96c63e70290b371c6a6a324f7498e23b8bba091a5ba93325
+size 498652017

relation_mapping.json

@@ -0,0 +1 @@
+{"accuracy": 0.8001190476190476, "prediction": [{"source": ["solar system", "sun", "planet", "mass", "attracts", "revolves", "gravity"], "true": ["atom", "nucleus", "electron", "charge", "attracts", "revolves", "electromagnetism"], "pred": ["electron", "atom", "nucleus", "charge", "attracts", "revolves", "electromagnetism"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.7947985265310452, "similarity_true": 0.7864812442673335}, {"source": ["water", "flows", "pressure", "water tower", "bucket", "filling", "emptying", "hydrodynamics"], "true": ["heat", "transfers", "temperature", "burner", "kettle", "heating", "cooling", "thermodynamics"], "pred": ["temperature", "transfers", "heat", "heating", "kettle", "burner", "cooling", "thermodynamics"], "alignment_match": false, "accuracy": 0.5, "similarity": 0.7490269508432464, "similarity_true": 0.7475804797256173}, {"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": 0.7503301451832284, "similarity_true": 0.7503301451832284}, {"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": 0.8099025054789661, "similarity_true": 0.8099025054789661}, {"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": 0.7660256460170678, "similarity_true": 0.7589492282937054}, {"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": 0.8364050965656179, "similarity_true": 0.8228878676810606}, {"source": ["breeds", "selection", "conformance", "artificial", "popularity", "breeding", "domesticated"], "true": ["species", "competition", "adaptation", "natural", "fitness", "mating", "wild"], "pred": ["species", "competition", "fitness", "natural", "adaptation", "mating", "wild"], "alignment_match": false, "accuracy": 0.7142857142857143, "similarity": 0.7637972256843206, "similarity_true": 0.7630792765324248}, {"source": ["ball", "billiards", "speed", "table", "bouncing", "moving", "slow", "fast"], "true": ["molecules", "gas", "temperature", "container", "pressing", "moving", "cold", "hot"], "pred": ["molecules", "gas", "pressing", "container", "temperature", "moving", "cold", "hot"], "alignment_match": false, "accuracy": 0.75, "similarity": 0.7563973788327476, "similarity_true": 0.7538429383709471}, {"source": ["computer", "processing", "erasing", "write", "read", "memory", "outputs", "inputs", "bug"], "true": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "pred": ["mind", "thinking", "forgetting", "memorize", "remember", "memory", "muscles", "senses", "mistake"], "alignment_match": true, "accuracy": 1, "similarity": 0.75032197651817, "similarity_true": 0.75032197651817}, {"source": ["slot machines", "reels", "spinning", "winning", "losing"], "true": ["bacteria", "genes", "mutating", "reproducing", "dying"], "pred": ["genes", "reproducing", "bacteria", "mutating", "dying"], "alignment_match": false, "accuracy": 0.2, "similarity": 0.682516873014841, "similarity_true": 0.6780339381648055}, {"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": 0.7449754419622724, "similarity_true": 0.7449754419622724}, {"source": ["buyer", "merchandise", "buying", "selling", "returning", "valuable", "worthless"], "true": ["believer", "belief", "accepting", "advocating", "rejecting", "true", "false"], "pred": ["believer", "advocating", "belief", "accepting", "rejecting", "true", "false"], "alignment_match": false, "accuracy": 0.5714285714285714, "similarity": 0.7374566341038511, "similarity_true": 0.7309577679029111}, {"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": 0.7094526992601076, "similarity_true": 0.7094526992601076}, {"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": 0.7606483483254272, "similarity_true": 0.7606483483254272}, {"source": ["money", "allocate", "budget", "effective", "cheap", "expansive"], "true": ["time", "invest", "schedule", "efficient", "quick", "slow"], "pred": ["time", "invest", "schedule", "slow", "quick", "efficient"], "alignment_match": false, "accuracy": 0.6666666666666666, "similarity": 0.797662803114076, "similarity_true": 0.7959334739740241}, {"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": 0.7851878855243125, "similarity_true": 0.7851878855243125}, {"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": 0.6819180179843746, "similarity_true": 0.6819180179843746}, {"source": ["object", "hold", "weight", "heavy", "light"], "true": ["idea", "understand", "analyze", "important", "trivial"], "pred": ["idea", "understand", "trivial", "important", "analyze"], "alignment_match": false, "accuracy": 0.6, "similarity": 0.7337459658992304, "similarity_true": 0.7313624122281329}, {"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": 0.7414432826891104, "similarity_true": 0.7414432826891104}, {"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": 0.750532352352461, "similarity_true": 0.750532352352461}]}

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/nce_logout.average.c.1",
+  "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": "nce_logout", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 5, "batch": 128, "lr": 5e-06, "lr_decay": false, "lr_warmup": 1, "weight_decay": 0, "random_seed": 1, "exclude_relation": null, "n_sample": 320, "gradient_accumulation": 8, "relation_level": null, "data_level": "child"}

validation_loss.json

@@ -0,0 +1 @@
+{"split": "validation", "loss": 9.140040714529496, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null, "level": "child"}