lisaterumi commited on
Commit
38f8efd
1 Parent(s): 1b435c8
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: "pt"
3
+ widget:
4
+ - text: "Dispneia venoso central em subclavia D duplolumen recebendo solução salina e glicosada em BI."
5
+ - text: "Paciente com Sepse pulmonar em D8 tazocin (paciente não recebeu por 2 dias Atb)."
6
+ - text: "FOI REALIZADO CURSO DE ATB COM LEVOFLOXACINA POR 7 DIAS."
7
+
8
+ datasets:
9
+ - SemClinBr
10
+ thumbnail: "https://raw.githubusercontent.com/HAILab-PUCPR/BioBERTpt/master/images/logo-biobertpr1.png"
11
+ ---
12
+
13
+ # Portuguese Clinical NER - Disease
14
+
15
+ The Disease NER model is part of the [BioBERTpt project](https://www.aclweb.org/anthology/2020.clinicalnlp-1.7/), where 13 models of clinical entities (compatible with UMLS) were trained. All NER model from "pucpr" user was trained from the Brazilian clinical corpus [SemClinBr](https://github.com/HAILab-PUCPR/SemClinBr), with 10 epochs and IOB2 format, from BioBERTpt(all) model.
16
+
17
+ ## Questions?
18
+
19
+ Post a Github issue on the [BioBERTpt repo](https://github.com/HAILab-PUCPR/BioBERTpt).
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pucpr/biobertpt-all",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "directionality": "bidi",
9
+ "eos_token_ids": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-DiseaseOrSyndrome",
17
+ "2": "I-DiseaseOrSyndrome"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "O": 0,
23
+ "B-DiseaseOrSyndrome": 1,
24
+ "I-DiseaseOrSyndrome": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": null,
33
+ "pooler_fc_size": 768,
34
+ "pooler_num_attention_heads": 12,
35
+ "pooler_num_fc_layers": 3,
36
+ "pooler_size_per_head": 128,
37
+ "pooler_type": "first_token_transform",
38
+ "position_embedding_type": "absolute",
39
+ "transformers_version": "4.8.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 119547
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa3630402dea4930754b890f9ac022201a9c0c7ad3b49d3a0bb2c436dbbdb50
3
+ size 709144049
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "max_len": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff