mmarimon commited on
Commit
1a3105b
1 Parent(s): 5c1e186

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -18
README.md CHANGED
@@ -32,19 +32,66 @@ widget:
32
  ---
33
 
34
  # Spanish RoBERTa-base biomedical model finetuned for the Named Entity Recognition (NER) task on the PharmaCoNER dataset.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  A fine-tuned version of the [bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) model, a [RoBERTa](https://arxiv.org/abs/1907.11692) base model and has been pre-trained using the largest Spanish biomedical corpus known to date, composed of biomedical documents, clinical cases and EHR documents for a total of 1.1B tokens of clean and deduplicated text processed.
36
 
37
  For more details about the corpora and training, check the _bsc-bio-ehr-es_ model card.
38
 
39
- ## Dataset
 
 
 
 
 
 
 
40
  The dataset used is [PharmaCoNER](https://huggingface.co/datasets/PlanTL-GOB-ES/pharmaconer), a NER dataset annotated with substances, compounds and proteins entities. For further information, check the [official website](https://temu.bsc.es/pharmaconer/).
41
 
42
- ## Evaluation and results
43
  F1 Score: 0.8913
44
 
45
  For evaluation details visit our [GitHub repository](https://github.com/PlanTL-GOB-ES/lm-biomedical-clinical-es).
46
 
47
- ## Citing
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  If you use these models, please cite our work:
49
 
50
  ```bibtext
@@ -71,23 +118,11 @@ If you use these models, please cite our work:
71
  }
72
  ```
73
 
74
- ## Copyright
75
-
76
- Copyright by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) (2022)
77
-
78
- ## Licensing information
79
-
80
- [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
81
-
82
- ## Funding
83
-
84
- This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL.
85
-
86
- ## Disclaimer
87
 
88
  The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions.
89
 
90
- When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of artificial intelligence.
91
 
92
  In no event shall the owner of the models (SEDIA – State Secretariat for digitalization and artificial intelligence) nor the creator (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models.
93
 
@@ -96,4 +131,4 @@ Los modelos publicados en este repositorio tienen una finalidad generalista y es
96
 
97
  Cuando terceros desplieguen o proporcionen sistemas y/o servicios a otras partes usando alguno de estos modelos (o utilizando sistemas basados en estos modelos) o se conviertan en usuarios de los modelos, deben tener en cuenta que es su responsabilidad mitigar los riesgos derivados de su uso y, en todo caso, cumplir con la normativa aplicable, incluyendo la normativa en materia de uso de inteligencia artificial.
98
 
99
- En ningún caso el propietario de los modelos (SEDIA – Secretaría de Estado de Digitalización e Inteligencia Artificial) ni el creador (BSC – Barcelona Supercomputing Center) serán responsables de los resultados derivados del uso que hagan terceros de estos modelos.
 
32
  ---
33
 
34
  # Spanish RoBERTa-base biomedical model finetuned for the Named Entity Recognition (NER) task on the PharmaCoNER dataset.
35
+
36
+ ## Table of contents
37
+ <details>
38
+ <summary>Click to expand</summary>
39
+
40
+ - [Model description](#model-description)
41
+ - [Intended uses and limitations](#intended-use)
42
+ - [How to use](#how-to-use)
43
+ - [Limitations and bias](#limitations-and-bias)
44
+ - [Training](#training)
45
+ - [Evaluation](#evaluation)
46
+ - [Additional information](#additional-information)
47
+ - [Author](#author)
48
+ - [Contact information](#contact-information)
49
+ - [Copyright](#copyright)
50
+ - [Licensing information](#licensing-information)
51
+ - [Funding](#funding)
52
+ - [Citing information](#citing-information)
53
+ - [Disclaimer](#disclaimer)
54
+
55
+ </details>
56
+
57
+ ## Model description
58
  A fine-tuned version of the [bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) model, a [RoBERTa](https://arxiv.org/abs/1907.11692) base model and has been pre-trained using the largest Spanish biomedical corpus known to date, composed of biomedical documents, clinical cases and EHR documents for a total of 1.1B tokens of clean and deduplicated text processed.
59
 
60
  For more details about the corpora and training, check the _bsc-bio-ehr-es_ model card.
61
 
62
+ ## Intended uses and limitations
63
+
64
+ ## How to use
65
+
66
+ ## Limitations and bias
67
+ At the time of submission, no measures have been taken to estimate the bias embedded in the model. However, we are well aware that our models may be biased since the corpora have been collected using crawling techniques on multiple web sources. We intend to conduct research in these areas in the future, and if completed, this model card will be updated.
68
+
69
+ ## Training
70
  The dataset used is [PharmaCoNER](https://huggingface.co/datasets/PlanTL-GOB-ES/pharmaconer), a NER dataset annotated with substances, compounds and proteins entities. For further information, check the [official website](https://temu.bsc.es/pharmaconer/).
71
 
72
+ ## Evaluation
73
  F1 Score: 0.8913
74
 
75
  For evaluation details visit our [GitHub repository](https://github.com/PlanTL-GOB-ES/lm-biomedical-clinical-es).
76
 
77
+ ## Additional information
78
+
79
+ ### Author
80
+ Text Mining Unit (TeMU) at the Barcelona Supercomputing Center ([email protected])
81
+
82
+ ### Contact information
83
+ For further information, send an email to <[email protected]>
84
+
85
+ ### Copyright
86
+ Copyright by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) (2022)
87
+
88
+ ### Licensing information
89
+ [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
90
+
91
+ ### Funding
92
+ This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL.
93
+
94
+ ## Citing information
95
  If you use these models, please cite our work:
96
 
97
  ```bibtext
 
118
  }
119
  ```
120
 
121
+ ### Disclaimer
 
 
 
 
 
 
 
 
 
 
 
 
122
 
123
  The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions.
124
 
125
+ When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of artificial intelligence.
126
 
127
  In no event shall the owner of the models (SEDIA – State Secretariat for digitalization and artificial intelligence) nor the creator (BSC – Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties of these models.
128
 
 
131
 
132
  Cuando terceros desplieguen o proporcionen sistemas y/o servicios a otras partes usando alguno de estos modelos (o utilizando sistemas basados en estos modelos) o se conviertan en usuarios de los modelos, deben tener en cuenta que es su responsabilidad mitigar los riesgos derivados de su uso y, en todo caso, cumplir con la normativa aplicable, incluyendo la normativa en materia de uso de inteligencia artificial.
133
 
134
+ En ningún caso el propietario de los modelos (SEDIA – Secretaría de Estado de Digitalización e Inteligencia Artificial) ni el creador (BSC – Barcelona Supercomputing Center) serán responsables de los resultados derivados del uso que hagan terceros de estos modelos.