Update README.md

README.md

@@ -1,17 +1,48 @@
+
 ---
+language: 
+  - pt
+thumbnail: "Portuguese SBERT for the Legal Domain"
 pipeline_tag: sentence-similarity
 tags:
 - sentence-transformers
-- feature-extraction
 - sentence-similarity
 - transformers
+datasets:
+- assin
+- assin2
+- stsb_multi_mt
+- rufimelo/PortugueseLegalSentences-v1
+widget:
+- source_sentence: "O advogado apresentou as provas ao juíz."
+  sentences:
+    - "O juíz leu as provas."
+    - "O juíz leu o recurso."
+    - "O juíz atirou uma pedra."
+  example_title: "Example 1"
+model-index:
+- name: BERTimbau
+  results:
+  - task:
+      name: STS
+      type: STS
+    metrics:
+      - name: Pearson Correlation - assin Dataset
+        type: Pearson Correlation
+        value: xxxxx 
+      - name: Pearson Correlation - assin2 Dataset
+        type: Pearson Correlation
+        value: xxxxx
+      - name: Pearson Correlation - stsb_multi_mt pt Dataset
+        type: Pearson Correlation
+        value: xxxxx
 ---
 
-# {MODEL_NAME}
-
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+# rufimelo/Legal-BERTimbau-base-TSDAE-sts
 
-<!--- Describe your model here -->
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+rufimelo/Legal-BERTimbau-base-TSDAE-sts is based on Legal-BERTimbau-large which derives from [BERTimbau](https://huggingface.co/neuralmind/bert-large-portuguese-cased) large.
+It is adapted to the Portuguese legal domain and trained for STS on portuguese datasets.
 
 ## Usage (Sentence-Transformers)
 
@@ -25,9 +56,9 @@ Then you can use the model like this:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+sentences = ["Isto é um exemplo", "Isto é um outro exemplo"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('rufimelo/Legal-BERTimbau-base-TSDAE-sts')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -35,23 +66,26 @@ print(embeddings)
 
 
 ## Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
 
 ```python
 from transformers import AutoTokenizer, AutoModel
 import torch
 
 
-def cls_pooling(model_output, attention_mask):
-    return model_output[0][:,0]
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
 
 
 # Sentences we want sentence embeddings for
 sentences = ['This is an example sentence', 'Each sentence is converted']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('rufimelo/Legal-BERTimbau-base-TSDAE-sts')
+model = AutoModel.from_pretrained('rufimelo/Legal-BERTimbau-base-TSDAE-sts')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -60,63 +94,62 @@ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tenso
 with torch.no_grad():
     model_output = model(**encoded_input)
 
-# Perform pooling. In this case, cls pooling.
-sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
 
 print("Sentence embeddings:")
 print(sentence_embeddings)
 ```
 
 
-
-## Evaluation Results
-
-<!--- Describe how your model was evaluated -->
-
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
-
-
+## Evaluation Results STS
+
+
+| Model| Assin | Assin2|stsb_multi_mt pt| avg|
+| ---------------------------------------- | ---------- | ---------- |---------- |---------- |
+| Legal-BERTimbau-sts-base| 0.71457| 0.73545 | 0.72383|0.72462|
+| Legal-BERTimbau-sts-base-ma| 0.74874 | 0.79532|0.82254 |0.78886|
+| Legal-BERTimbau-sts-base-ma-v2| 0.75481 | 0.80262|0.82178|0.79307|
+| Legal-BERTimbau-sts-large| 0.76629| 0.82357 | 0.79120|0.79369|
+| Legal-BERTimbau-sts-large-v2| 0.76299 | 0.81121|0.81726 |0.79715|
+| Legal-BERTimbau-sts-large-ma| 0.76195| 0.81622 | 0.82608|0.80142|
+| Legal-BERTimbau-sts-large-ma-v2| 0.7836| 0.8462| 0.8261| 0.81863|
+| Legal-BERTimbau-sts-large-ma-v3| 0.7749| **0.8470**| 0.8364| **0.81943**|
+| ---------------------------------------- | ---------- |---------- |---------- |---------- |
+| BERTimbau base Fine-tuned for STS|**0.78455** | 0.80626|0.82841|0.80640|
+| BERTimbau large Fine-tuned for STS|0.78193 | 0.81758|0.83784|0.81245|
+| ---------------------------------------- | ---------- |---------- |---------- |---------- |
+| paraphrase-multilingual-mpnet-base-v2| 0.71457| 0.79831 |0.83999 |0.78429|
+| paraphrase-multilingual-mpnet-base-v2 Fine-tuned with assin(s)| 0.77641|0.79831   |**0.84575**|0.80682|
 ## Training
-The model was trained with the parameters:
 
-**DataLoader**:
+rufimelo/Legal-BERTimbau-base-TSDAE-sts is based on rufimelo/Legal-BERTimbau-base-TSDAE which derives from [BERTimbau](https://huggingface.co/neuralmind/bert-base-portuguese-cased) large.
 
-`torch.utils.data.dataloader.DataLoader` of length 2157 with parameters:
-```
-{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
-```
-
-**Loss**:
+rufimelo/Legal-BERTimbau-base-TSDAE was trained with TSDAE: 50000 cleaned documents (https://huggingface.co/datasets/rufimelo/PortugueseLegalSentences-v1)
+'lr': 1e-5
 
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
-
-Parameters of the fit()-Method:
-```
-{
-    "epochs": 5,
-    "evaluation_steps": 0,
-    "evaluator": "NoneType",
-    "max_grad_norm": 1,
-    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
-    "optimizer_params": {
-        "lr": 1e-05
-    },
-    "scheduler": "WarmupLinear",
-    "steps_per_epoch": null,
-    "warmup_steps": 1079,
-    "weight_decay": 0.01
-}
-```
+It was trained for Semantic Textual Similarity, being submitted to a fine tuning stage with the [assin](https://huggingface.co/datasets/assin), [assin2](https://huggingface.co/datasets/assin2) and [stsb_multi_mt pt](https://huggingface.co/datasets/stsb_multi_mt) datasets. 'lr': 1e-5
 
 
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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
 
-<!--- Describe where people can find more information -->
+If you use this work, please cite BERTimbau's work:
+
+```bibtex
+@inproceedings{souza2020bertimbau,
+  author    = {F{\'a}bio Souza and
+               Rodrigo Nogueira and
+               Roberto Lotufo},
+  title     = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
+  booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
+  year      = {2020}
+}
+```