ner model

README.md

@@ -0,0 +1,19 @@
+---
+language: "pt"
+widget:
+- text: "Dispneia venoso central em subclavia D duplolumen recebendo solução salina e glicosada em BI."
+- text: "Paciente com Sepse pulmonar em D8 tazocin (paciente não recebeu por 2 dias Atb)."
+- text: "FOI REALIZADO CURSO DE ATB COM LEVOFLOXACINA POR 7 DIAS."
+
+datasets: 
+- SemClinBr
+thumbnail: "https://raw.githubusercontent.com/HAILab-PUCPR/BioBERTpt/master/images/logo-biobertpr1.png"
+---
+
+# Portuguese Clinical NER - Disease
+
+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.
+
+## Questions?
+
+Post a Github issue on the [BioBERTpt repo](https://github.com/HAILab-PUCPR/BioBERTpt).

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "pucpr/biobertpt-all",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "eos_token_ids": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DiseaseOrSyndrome",
+    "2": "I-DiseaseOrSyndrome"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "B-DiseaseOrSyndrome": 1,
+    "I-DiseaseOrSyndrome": 2
+  },
+  "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": null,
+  "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": "4.8.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa3630402dea4930754b890f9ac022201a9c0c7ad3b49d3a0bb2c436dbbdb50
+size 709144049

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "max_len": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}