Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.

.gitattributes

@@ -1,35 +1,4 @@
-*.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
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
+test_data.pickle filter=lfs diff=lfs merge=lfs -text
+val_data.pickle filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

LT_training_config.json

@@ -0,0 +1,29 @@
+{
+  "model_save_dir": "models",
+  "model_save_name": "lt-historicjapanesecompanies-comp-prod-ind_supcon_full",
+  "opt_model_description": "This model was trained on a dataset of historic Japanese companies, products, industry, addresses, and shareholders. Take a look at our paper for more details. The task is to link indices of japanese companies",
+  "opt_model_lang": "ja",
+  "train_batch_size": 64,
+  "num_epochs": 50,
+  "warm_up_perc": 1,
+  "learning_rate": 2e-05,
+  "loss_type": "supcon",
+  "val_perc": 0.2,
+  "wandb_names": {
+    "id": "econabhishek",
+    "run": "lt-historicjapanesecompanies-comp-prod-ind_supcon_full",
+    "project": "linkage",
+    "entity": "econabhishek"
+  },
+  "add_pooling_layer": false,
+  "large_val": true,
+  "eval_steps_perc": 0.5,
+  "test_at_end": true,
+  "save_val_test_pickles": true,
+  "val_query_prop": 0.5,
+  "loss_params": {},
+  "eval_type": "classification",
+  "training_dataset": "dataframe",
+  "base_model_path": "oshizo/sbert-jsnli-luke-japanese-base-lite",
+  "best_model_path": "models/lt-historicjapanesecompanies-comp-prod-ind_supcon_full"
+}

README.md

@@ -0,0 +1,146 @@
+---
+pipeline_tag: sentence-similarity
+language: 
+- ja
+tags:
+- linktransformer
+- sentence-transformers
+- sentence-similarity
+- tabular-classification
+
+---
+
+# {MODEL_NAME}
+
+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. 
+
+
+This model has been fine-tuned on the model : oshizo/sbert-jsnli-luke-japanese-base-lite. It is pretrained for the language : - ja.
+
+
+This model was trained on a dataset of historic Japanese companies, products, industry, addresses, and shareholders. Take a look at our paper for more details. The task is to link indices of japanese companies
+
+## Usage (LinkTransformer)
+
+Using this model becomes easy when you have [LinkTransformer](https://github.com/dell-research-harvard/linktransformer) installed:
+
+```
+pip install -U linktransformer
+```
+
+Then you can use the model like this:
+
+```python
+import linktransformer as lt
+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 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. 
+
+
+```python
+
+##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!
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+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 16 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": 50,
+    "evaluation_steps": 8,
+    "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": 800,
+    "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})
+)
+```
+
+## Citing & Authors
+
+```
+@misc{arora2023linktransformer,
+                  title={LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models},
+                  author={Abhishek Arora and Melissa Dell},
+                  year={2023},
+                  eprint={2309.00789},
+                  archivePrefix={arXiv},
+                  primaryClass={cs.CL}
+                }
+
+```

added_tokens.json

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

binary_classification_evaluation_eval_results.csv

@@ -0,0 +1,3 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,0,0.9382022471910112,0.8532869815826416,0.7636363636363636,0.7,0.84,0.8262333869934082,0.8184099257358792,0.9382022471910112,84.1578369140625,0.7572815533980584,0.7358490566037735,0.78,89.29296112060547,0.8270661393011416,0.9438202247191011,4.08632755279541,0.7872340425531915,0.8409090909090909,0.74,4.08632755279541,0.8277502672701681,0.8848314606741573,44.88762664794922,0.5925925925925927,0.5517241379310345,0.64,43.54036331176758,0.5417359362559628
+0,0,0.9382022471910112,0.8532869815826416,0.7636363636363636,0.7,0.84,0.8262333869934082,0.8184099257358792,0.9382022471910112,84.1578369140625,0.7572815533980584,0.7358490566037735,0.78,89.29296112060547,0.8270661393011416,0.9438202247191011,4.08632755279541,0.7872340425531915,0.8409090909090909,0.74,4.08632755279541,0.8277502672701681,0.8848314606741573,44.88762283325195,0.5925925925925927,0.5517241379310345,0.64,43.54036331176758,0.5417359362559628

binary_classification_evaluation_test_results.csv

@@ -0,0 +1,3 @@
+epoch,steps,cossim_accuracy,cossim_accuracy_threshold,cossim_f1,cossim_precision,cossim_recall,cossim_f1_threshold,cossim_ap,manhattan_accuracy,manhattan_accuracy_threshold,manhattan_f1,manhattan_precision,manhattan_recall,manhattan_f1_threshold,manhattan_ap,euclidean_accuracy,euclidean_accuracy_threshold,euclidean_f1,euclidean_precision,euclidean_recall,euclidean_f1_threshold,euclidean_ap,dot_accuracy,dot_accuracy_threshold,dot_f1,dot_precision,dot_recall,dot_f1_threshold,dot_ap
+0,0,0.9578651685393258,0.7885568141937256,0.854368932038835,0.9166666666666666,0.8,0.7569339871406555,0.9027201028709122,0.9606741573033708,121.89360046386719,0.86,0.9555555555555556,0.7818181818181819,121.89360046386719,0.9092811528662349,0.9606741573033708,5.6210103034973145,0.8653846153846154,0.9183673469387755,0.8181818181818182,5.979313373565674,0.9083606695270187,0.9410112359550562,58.51844024658203,0.7789473684210527,0.925,0.6727272727272727,58.51844024658203,0.8613143757051128
+0,0,0.9578651685393258,0.7794706225395203,0.845360824742268,0.9761904761904762,0.7454545454545455,0.7794706225395203,0.9070055457080543,0.9578651685393258,119.23606872558594,0.8545454545454545,0.8545454545454545,0.8545454545454545,140.44253540039062,0.9139460658879931,0.9578651685393258,5.471532344818115,0.8545454545454545,0.8545454545454545,0.8545454545454545,6.480866432189941,0.9147327683242549,0.9241573033707865,56.068626403808594,0.7518796992481204,0.6410256410256411,0.9090909090909091,46.432830810546875,0.8419716262659404

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/abhishekarora/.cache/torch/sentence_transformers/oshizo_sbert-jsnli-luke-japanese-base-lite/",
+  "architectures": [
+    "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c43b11600beb431e99a5285efa15ec24aba97c430c0108c0b0a8075c5beb129
+size 532299592

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "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

@@ -0,0 +1,73 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

test_data.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d2b470c96d3e8108f0a18ffe2707122bb0f30bf07bc11666de18b384714b0c
+size 206402

test_results_allmethods.csv

@@ -0,0 +1,2 @@
+edit_distance,edit_distance_threshold,SBERT,SBERT_threshold,LT ZS Wiki,LT ZS Wiki_threshold,LT,LT_threshold,OpenAI,OpenAI_threshold
+0.267639902676399,0.7790753674033062,0.6902654867256638,0.8263489127309215,0.723404255319149,0.6465095054004382,0.8367346938775511,0.7741220046283592,0.8627450980392157,0.9252961885425512

tokenizer_config.json

@@ -0,0 +1,106 @@
+{
+  "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>"
+  ],
+  "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>",
+  "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "unk_token": "<unk>"
+}

val_data.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9a840c70377691526c516f49b5712585452cf7e7f6e0a30ce621fadb84b6f6
+size 211003