fernandogd97 commited on
Commit
5012ad1
verified
1 Parent(s): 2d8d089

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -21,7 +21,7 @@ tags:
21
 
22
  ClinLinker-KB-P is a state-of-the-art bi-encoder model for medical entity linking (MEL) in Spanish, optimized for clinical domain tasks. It enriches concept representations by incorporating not only synonyms but also hierarchical relationships (parents) from the UMLS and SNOMED-CT ontologies. The model was trained with a contrastive-learning strategy using hard negative mining and multi-similarity loss.
23
 
24
- ## Intended Use
25
  - **Domain**: Spanish Clinical NLP
26
  - **Tasks**: Entity linking (diseases, symptoms, procedures) to SNOMED-CT
27
  - **Evaluated On**: DisTEMIST, MedProcNER, SympTEMIST
@@ -39,7 +39,7 @@ ClinLinker-KB-P is a state-of-the-art bi-encoder model for medical entity linkin
39
 
40
  *Results correspond to the cleaned gold-standard version (no "NO CODE" or "COMPOSITE").*
41
 
42
- ## Usage
43
 
44
  ```python
45
  from transformers import AutoModel, AutoTokenizer
@@ -62,7 +62,7 @@ For scalable retrieval, use [Faiss](https://github.com/facebookresearch/faiss) o
62
  - The model is optimized for Spanish clinical data and may underperform outside this domain.
63
  - Expert validation is advised in critical applications.
64
 
65
- ## Citation
66
 
67
  > Gallego, Fernando and L贸pez-Garc铆a, Guillermo and Gasco, Luis and Krallinger, Martin and Veredas, Francisco J., Clinlinker-Kb: Clinical Entity Linking in Spanish with Knowledge-Graph Enhanced Biencoders. Available at SSRN:http://dx.doi.org/10.2139/ssrn.4939986.
68
 
 
21
 
22
  ClinLinker-KB-P is a state-of-the-art bi-encoder model for medical entity linking (MEL) in Spanish, optimized for clinical domain tasks. It enriches concept representations by incorporating not only synonyms but also hierarchical relationships (parents) from the UMLS and SNOMED-CT ontologies. The model was trained with a contrastive-learning strategy using hard negative mining and multi-similarity loss.
23
 
24
+ ## 馃挕 Intended Use
25
  - **Domain**: Spanish Clinical NLP
26
  - **Tasks**: Entity linking (diseases, symptoms, procedures) to SNOMED-CT
27
  - **Evaluated On**: DisTEMIST, MedProcNER, SympTEMIST
 
39
 
40
  *Results correspond to the cleaned gold-standard version (no "NO CODE" or "COMPOSITE").*
41
 
42
+ ## 馃И Usage
43
 
44
  ```python
45
  from transformers import AutoModel, AutoTokenizer
 
62
  - The model is optimized for Spanish clinical data and may underperform outside this domain.
63
  - Expert validation is advised in critical applications.
64
 
65
+ ## 馃摎 Citation
66
 
67
  > Gallego, Fernando and L贸pez-Garc铆a, Guillermo and Gasco, Luis and Krallinger, Martin and Veredas, Francisco J., Clinlinker-Kb: Clinical Entity Linking in Spanish with Knowledge-Graph Enhanced Biencoders. Available at SSRN:http://dx.doi.org/10.2139/ssrn.4939986.
68