Updated model with better training and evaluation. Test and val data included as pickle files.

.gitattributes

@@ -1,37 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
-.git/lfs/objects/2c/54/2c547cd0200d5e2941a0df1be6f08c9c58aa7909c52edc93b34fd74a26360708 filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/38/03/38038b2d482f03da65b16b695cca791699e9d40235edd0dbe368b855c05ca162 filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -3,5 +3,7 @@
   "pooling_mode_cls_token": false,
   "pooling_mode_mean_tokens": true,
   "pooling_mode_max_tokens": false,
-  "pooling_mode_mean_sqrt_len_tokens": false
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
 }

LT_training_config.json

@@ -1,27 +1,29 @@
 {
   "model_save_dir": "models",
-  "model_save_name": "check2",
-  "opt_model_description": null,
-  "opt_model_lang": null,
+  "model_save_name": "check",
+  "opt_model_description": "test",
+  "opt_model_lang": "jp",
   "train_batch_size": 64,
   "num_epochs": 1,
   "warm_up_perc": 1,
-  "learning_rate": 2e-06,
+  "learning_rate": 2e-05,
+  "loss_type": "supcon",
   "val_perc": 0.2,
   "wandb_names": {
-    "project": "linkage",
-    "id": "econabhishek",
-    "run": "paraphrase-xlm-r-multilingual-v1-es",
-    "entity": "econabhishek"
+    "project": "linktransformer",
+    "id": "your-id",
+    "run": "run-name",
+    "entity": "your-id"
   },
   "add_pooling_layer": false,
   "large_val": true,
-  "eval_steps_perc": 0.1,
+  "eval_steps_perc": 0.5,
   "test_at_end": true,
   "save_val_test_pickles": true,
   "val_query_prop": 0.5,
-  "eval_type": "retrieval",
-  "training_dataset": "/mnt/122a7683-fa4b-45dd-9f13-b18cc4f4a187/deeprecordlinkage/linktransformer/src/linktransformer/data/es_mexican_products.xlsx",
-  "base_model_path": "hiiamsid/sentence_similarity_spanish_es",
-  "best_model_path": "models/check2"
+  "loss_params": {},
+  "eval_type": "classification",
+  "training_dataset": "dataframe",
+  "base_model_path": "oshizo/sbert-jsnli-luke-japanese-base-lite",
+  "best_model_path": "models/check"
 }

README.md

@@ -1,67 +1,84 @@
 ---
-pipeline_tag: text-classification
+pipeline_tag: sentence-similarity
 language: 
-- en
+- jp
 tags:
 - linktransformer
-- transformers
-- text-classification
+- sentence-transformers
+- sentence-similarity
 - tabular-classification
 
 ---
 
 # dell-research-harvard/linktransformer-models-test
 
-This model is part of the [LinkTransformer](https://linktransformer.github.io/) ecosystem. While rooted in the a standard HuggingFace Transformer, this specific instance is tailored for text classification tasks. It classifies input sentences or paragraphs into specific categories or labels, leveraging the power of transformer architectures.
+This is a [LinkTransformer](https://linktransformer.github.io/) model. At its core this model this is a sentence transformer model [sentence-transformers](https://www.SBERT.net) model- it just wraps around the class. 
+It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more.
+Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. 
+It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+Take a look at the documentation of [sentence-transformers](https://www.sbert.net/index.html) if you want to use this model for more than what we support in our applications. 
 
-The base model for this classifier is: roberta. It is pretrained for the language: - en.
 
-Labels are mapped to integers as follows: 
+This model has been fine-tuned on the model : oshizo/sbert-jsnli-luke-japanese-base-lite. It is pretrained for the language : - jp.
 
-- Neither: 0
-- Protest: 1
-- Riot: 2
 
+test
 
-This is a LinkTransformer model for classification of text into 'Protest', 'Riot' or 'Neither' classes. It was trained on annotated newspaper articles.
+## Usage (LinkTransformer)
 
-## Usage with LinkTransformer
+Using this model becomes easy when you have [LinkTransformer](https://github.com/dell-research-harvard/linktransformer) installed:
 
-After installing [LinkTransformer](https://linktransformer.github.io/):
-
-```python
+```
 pip install -U linktransformer
 ```
 
-Employ the model for text classification tasks:
+Then you can use the model like this:
 
 ```python
 import linktransformer as lt
-df_clf_output = lt.classify_rows(df, on=["col_of_interest"], model="dell-research-harvard/linktransformer-models-test")
-```
+import pandas as pd
 
+##Load the two dataframes that you want to link. For example, 2 dataframes with company names that are written differently
+df1=pd.read_csv("data/df1.csv") ###This is the left dataframe with key CompanyName for instance
+df2=pd.read_csv("data/df2.csv") ###This is the right dataframe with key CompanyName for instance
+
+###Merge the two dataframes on the key column!
+df_merged = lt.merge(df1, df2, on="CompanyName", how="inner")
+
+##Done! The merged dataframe has a column called "score" that contains the similarity score between the two company names
+
+```
 
-## Training
 
-### Training your own LinkTransformer Classification Model
+## Training your own LinkTransformer model
+Any Sentence Transformers can be used as a backbone by simply adding a pooling layer.  Any other transformer on HuggingFace can also be used by specifying the option add_pooling_layer==True
+The model was trained using SupCon loss. 
+Usage can be found in the package docs. 
+The training config can be found in the repo with the name LT_training_config.json
+To replicate the training, you can download the file and specify the path in the config_path argument of the training function. You can also override the config by specifying the training_args argument.
+Here is an example. 
 
-With the provided tools, you can train a custom classification model:
 
 ```python
-from linktransformer import train_clf_model
-
-best_model_path, best_metric, label_map = train_clf_model(
-    data="path_to_dataset.csv",
-    model="you-model-path-or-name",
-    on=["col_of_interest"],
-    label_col_name="label_column_name",
-    lr=5e-5,
-    batch_size=16,
-    epochs=3
-)
+
+##Consider the example in the paper that has a dataset of Mexican products and their tariff codes from 1947 and 1948 and we want train a model to link the two tariff codes.
+saved_model_path = train_model(
+        model_path="hiiamsid/sentence_similarity_spanish_es",
+        dataset_path=dataset_path,
+        left_col_names=["description47"],
+        right_col_names=['description48'],
+        left_id_name=['tariffcode47'],
+        right_id_name=['tariffcode48'],
+        log_wandb=False,
+        config_path=LINKAGE_CONFIG_PATH,
+        training_args={"num_epochs": 1}
+    )
+
 ```
 
 
+You can also use this package for deduplication (clusters a df on the supplied key column). Merging a fine class (like product) to a coarse class (like HS code) is also possible.
+Read our paper and the documentation for more!
 
 
 
@@ -69,7 +86,50 @@ best_model_path, best_metric, label_map = train_clf_model(
 
 <!--- Describe how your model was evaluated -->
 
-Evaluation is typically based on metrics like accuracy, F1-score, precision, and recall.
+You can evaluate the model using the [LinkTransformer](https://github.com/dell-research-harvard/linktransformer) package's inference functions.
+We have provided a few datasets in the package for you to try out. We plan to host more datasets on Huggingface and our website (Coming soon) that you can take a look at.
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 10 with parameters:
+```
+{'batch_size': 64, 'sampler': 'torch.utils.data.dataloader._InfiniteConstantSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`linktransformer.modified_sbert.losses.SupConLoss_wandb` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 5,
+    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 10,
+    "weight_decay": 0.01
+}
+```
+
+
+
+
+LinkTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: LukeModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
 
 ## Citing & Authors
 
@@ -81,5 +141,6 @@ Evaluation is typically based on metrics like accuracy, F1-score, precision, and
                   eprint={2309.00789},
                   archivePrefix={arXiv},
                   primaryClass={cs.CL}
-}
+                }
+
 ```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ent2>": 32771,
+  "<ent>": 32770
+}

config.json

@@ -1,38 +1,32 @@
 {
-  "_name_or_path": "test_lt_clf/checkpoint-90",
+  "_name_or_path": "/mnt/122a7683-fa4b-45dd-9f13-b18cc4f4a187/deeprecordlinkage/linktransformer/models/check",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "LukeModel"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
   "bos_token_id": 0,
   "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "model_type": "luke",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.35.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
 }

config_sentence_transformers.json

@@ -1,7 +1,7 @@
 {
   "__version__": {
-    "sentence_transformers": "2.0.0",
-    "transformers": "4.10.2",
-    "pytorch": "1.9.0+cu102"
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.25.1",
+    "pytorch": "1.13.0+cu116"
   }
 }

entity_vocab.json

@@ -0,0 +1,6 @@
+{
+  "[MASK2]": 3,
+  "[MASK]": 0,
+  "[PAD]": 2,
+  "[UNK]": 1
+}

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38038b2d482f03da65b16b695cca791699e9d40235edd0dbe368b855c05ca162
-size 328517105
+oid sha256:ffff8b1e1118917383c8481ca5631e9b5a05616039a6f0039ad5d0fae975d7ed
+size 532299592

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 512,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
+size 841889

special_tokens_map.json

@@ -1,15 +1,75 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "additional_special_tokens": [
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,15 +1,108 @@
 {
-  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32769": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32770": {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32771": {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
+  "entity_mask2_token": "[MASK2]",
+  "entity_mask_token": "[MASK]",
+  "entity_pad_token": "[PAD]",
+  "entity_token_1": {
+    "__type": "AddedToken",
+    "content": "<ent>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false,
+    "special": false
+  },
+  "entity_token_2": {
+    "__type": "AddedToken",
+    "content": "<ent2>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false,
+    "special": false
+  },
+  "entity_unk_token": "[UNK]",
   "eos_token": "</s>",
-  "errors": "replace",
   "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
   "unk_token": "<unk>"
 }