Duplicate from ulysses-camara/legal-bert-pt-br

Co-authored-by: Augusto Nunes <augusnunes@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

0_Transformer/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

0_Transformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37bf2ba5b420399e84e94e109f5ca37f65a464b4fa6d95468a9a616bc5fd04eb
+size 435776311

0_Transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 32,
+  "do_lower_case": false
+}

0_Transformer/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

0_Transformer/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralmind/bert-base-portuguese-cased", "do_basic_tokenize": true, "never_split": null}

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
+}

README.md

@@ -0,0 +1,41 @@
+---
+language: pt
+license: mit
+tags:
+- sentence-transformers
+duplicated_from: ulysses-camara/legal-bert-pt-br
+---
+
+# LegalBERTPT-br
+
+LegalBERTPT-br is a trained sentence embedding using SimCSE, a contrastive learning framework, coupled with the Portuguese pre-trained language model named [BERTimbau](https://huggingface.co/neuralmind/bert-base-portuguese-cased). 
+
+
+# Corpora
+
+– From [this site](https://www2.camara.leg.br/transparencia/servicos-ao-cidadao/participacao-popular), we used the column `Conteudo` with 215,713 comments. We removed the comments from PL 3723/2019, PEC 471/2005, and Hashtag Corpus, in order to avoid bias.
+
+– From [this site](https://www2.camara.leg.br/transparencia/servicos-ao-cidadao/participacao-popular), we also used 147,008 bills. From these projects, we used the summary field named `txtEmenta` and the project core text named `txtExplicacaoEmenta`.
+
+– From Political Speeches, we used 462,831 texts, specifically, we used the columns: `sumario`, `textodiscurso`, and `indexacao`.
+
+These corpora were segmented into sentences and concatenated, producing 2,307,426 sentences.
+
+
+# Citing and Authors
+
+If you find this model helpful, feel free to cite our publication [Evaluating Topic Models in Portuguese Political Comments About Bills from Brazil’s Chamber of Deputies](https://link.springer.com/chapter/10.1007/978-3-030-91699-2_8):
+```bibtex 
+@inproceedings{bracis,
+ author = {Nádia Silva and Marília Silva and Fabíola Pereira and João Tarrega and João Beinotti and Márcio Fonseca and Francisco Andrade and André Carvalho},
+ title = {Evaluating Topic Models in Portuguese Political Comments About Bills from Brazil’s Chamber of Deputies},
+ booktitle = {Anais da X Brazilian Conference on Intelligent Systems},
+ location = {Online},
+ year = {2021},
+ keywords = {},
+ issn = {0000-0000},
+ publisher = {SBC},
+ address = {Porto Alegre, RS, Brasil},
+ url = {https://sol.sbc.org.br/index.php/bracis/article/view/19061}
+}
+```

config.json

@@ -0,0 +1,3 @@
+{
+  "__version__": "1.2.0"
+}

modules.json

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