Basic Spacy BioNER pipeline, with a RoBERTa-based model [bsc-bio-ehr-es] (https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) and a dataset, Pharmaconer, a NER dataset annotated with substances, compounds and proteins entities. For further information, check the official website. Visit our GitHub repository. This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL
1
15 commits
2 linked in READMEs
updated Nov 23, 2022
README
Basic Spacy BioNER pipeline, with a RoBERTa-based model [bsc-bio-ehr-es] (https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) and a dataset, Pharmaconer, a NER dataset annotated with substances, compounds and proteins entities. For further information, check the official website. Visit our GitHub repository. This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL
| Feature | Description |
|---|---|
| Name | es_pharmaconer_ner_trf |
| Version | 3.4.1 |
| spaCy | >=3.4.1,<3.5.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | mit |
| Author | The Text Mining Unit from Barcelona Supercomputing Center. |
| Copyright | Copyright by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) (2022) |
| Funding | This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL |
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels |
|---|---|
ner | NORMALIZABLES, NO_NORMALIZABLES, PROTEINAS, UNCLEAR |
Accuracy
| Type | Score |
|---|---|
ENTS_F | 91.09 |
ENTS_P | 90.67 |
ENTS_R | 91.53 |
TRANSFORMER_LOSS | 15719.51 |
NER_LOSS | 22469.88 |
Similar repos
Linked in READMEs
Basic Spacy BioNER pipeline, with a RoBERTa-based model [bsc-bio-ehr-es] (https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) and a dataset, Pharmaconer, a NER dataset annotated with substances, compounds and proteins entities. For further information, check the official website. Visit our GitHub repository. This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL
1
15 commits
2 linked in READMEs
updated Nov 23, 2022
README
Basic Spacy BioNER pipeline, with a RoBERTa-based model [bsc-bio-ehr-es] (https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) and a dataset, Pharmaconer, a NER dataset annotated with substances, compounds and proteins entities. For further information, check the official website. Visit our GitHub repository. This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL
| Feature | Description |
|---|---|
| Name | es_pharmaconer_ner_trf |
| Version | 3.4.1 |
| spaCy | >=3.4.1,<3.5.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | mit |
| Author | The Text Mining Unit from Barcelona Supercomputing Center. |
| Copyright | Copyright by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) (2022) |
| Funding | This work was funded by the Spanish State Secretariat for Digitalization and Artificial Intelligence (SEDIA) within the framework of the Plan-TL |
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels |
|---|---|
ner | NORMALIZABLES, NO_NORMALIZABLES, PROTEINAS, UNCLEAR |
Accuracy
| Type | Score |
|---|---|
ENTS_F | 91.09 |
ENTS_P | 90.67 |
ENTS_R | 91.53 |
TRANSFORMER_LOSS | 15719.51 |
NER_LOSS | 22469.88 |