Hugging Face's logo

Mykes
/
med_ner_SDDCS

Token Classification
Transformers
Safetensors
Russian
bert
biology
medical
Model card Files
xet
Community
Mykes commited on
Commit
c7a2d6b
·
verified ·
1 Parent(s): d051d2d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -19
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  base_model:
3
- - Babelscape/wikineural-multilingual-ner
4
  datasets:
5
  - Mykes/patient_queries_ner_SDDCS
6
  language:
@@ -14,9 +14,9 @@ tags:
14
 
15
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63565a3d58acee56a457f799/MqL0twwg_1DWKN7taDvQy.jpeg)
16
 
17
- # med_ner_SDDCS
18
- SDDCS - abbreviation for ner-entities SYMPTOMS, DISEASES, DRUGS, CITIES, SUBWAY STATIONS (additionally it is able to predict GENDER and AGE entities)
19
- This is a fine-tuned Named Entity Recognition (NER) model based on the Babelscape/wikineural-multilingual-ner model, designed to detect russian medical entities like diseases, drugs, symptoms, and more.
20
 
21
  # Model Details
22
  - Model Name: med_ner_SDDCS
@@ -37,24 +37,21 @@ This is a fine-tuned Named Entity Recognition (NER) model based on the Babelscap
37
  The fine-tuned model has achieved the following performance metrics:
38
 
39
  ```
40
- precision recall f1-score support
41
 
42
- AGE 0.99 1.00 1.00 904
43
- CITY 0.99 1.00 1.00 3796
44
- DISEASE 0.99 1.00 0.99 4814
45
- DRUG 0.99 0.99 0.99 4516
46
- GENDER 0.99 1.00 0.99 476
47
- SPECIALITY 0.93 0.98 0.96 3683
48
- SUBWAY 0.99 1.00 1.00 688
49
- SYMPTOM 0.99 0.99 0.99 8025
50
 
51
- micro avg 0.98 0.99 0.99 26902
52
- macro avg 0.98 0.99 0.99 26902
53
- weighted avg 0.98 0.99 0.99 26902
54
 
55
- Overall performance:
56
- Micro Avg: Precision = 0.98, Recall = 0.99, F1-Score = 0.99
57
- Macro Avg: Precision = 0.98, Recall = 0.99, F1-Score = 0.99
58
  How to Use
59
  ```
60
  You can use this model with the transformers library to perform Named Entity Recognition (NER) tasks in the russian medical domain, mainly for patient queries. Here's how to load and use the model:
 
1
  ---
2
  base_model:
3
+ - google-bert/bert-base-multilingual-uncased
4
  datasets:
5
  - Mykes/patient_queries_ner_SDDCS
6
  language:
 
14
 
15
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63565a3d58acee56a457f799/MqL0twwg_1DWKN7taDvQy.jpeg)
16
 
17
+ # med_ner_SDDCS
18
+ SDDCS - abbreviation for ner-entities SYMPTOMS, DISEASES, DRUGS, CITIES, SUBWAY STATIONS (additionall it is able to predict GENDER and AGE entities)
19
+ This is a fine-tuned Named Entity Recognition (NER) model based on the [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) model, designed to detect russian medical entities like diseases, drugs, symptoms, and more.
20
 
21
  # Model Details
22
  - Model Name: med_ner_SDDCS
 
37
  The fine-tuned model has achieved the following performance metrics:
38
 
39
  ```
40
+ precision recall f1-score support
41
 
42
+ AGE 0.99 1.00 0.99 706
43
+ CITY 0.99 1.00 1.00 2370
44
+ DISEASE 0.99 1.00 0.99 4841
45
+ DRUG 0.99 1.00 0.99 4546
46
+ GENDER 0.99 1.00 1.00 476
47
+ SPECIALITY 0.98 0.96 0.97 3673
48
+ SUBWAY 1.00 1.00 1.00 658
49
+ SYMPTOM 0.99 0.99 0.99 8022
50
 
51
+ micro avg 0.99 0.99 0.99 25292
52
+ macro avg 0.99 0.99 0.99 25292
53
+ weighted avg 0.99 0.99 0.99 25292
54
 
 
 
 
55
  How to Use
56
  ```
57
  You can use this model with the transformers library to perform Named Entity Recognition (NER) tasks in the russian medical domain, mainly for patient queries. Here's how to load and use the model: