MilosKosRad
commited on
Commit
•
ed03fce
1
Parent(s):
0494f32
Update README.md
Browse files
README.md
CHANGED
@@ -30,7 +30,7 @@ library_name: transformers
|
|
30 |
|
31 |
This model was created during the research collaboration between Bayer Pharma and The Institute for Artificial Intelligence Research and Development of Serbia.
|
32 |
The model is trained on 26 biomedical Named Entity (NE) classes and can perform zero-shot inference. It also can be further fine-tuned for new classes with just few examples (few-shot learning).
|
33 |
-
For more details about our method please see the paper named ["
|
34 |
|
35 |
Model takes two strings as input. String1 is NE label that is being searched in second string. String2 is short text where one wants to searc for NE (represented by String1).
|
36 |
Model outputs list of ones (corresponding to the found Named Entities) and zeros (corresponding to other non-NE tokens) of the Sring2.
|
@@ -145,12 +145,12 @@ Code used for training and testing the model is available at https://github.com/
|
|
145 |
|
146 |
If you use this model, or are inspired by it, please cite in your paper the following paper:
|
147 |
|
148 |
-
Košprdić M.,Prodanović N., Ljajić A., Bašaragin B., Milošević N., 2023.
|
149 |
|
150 |
or in bibtex:
|
151 |
```
|
152 |
@misc{kosprdic2023transformerbased,
|
153 |
-
title={
|
154 |
author={Miloš Košprdić and Nikola Prodanović and Adela Ljajić and Bojana Bašaragin and Nikola Milošević},
|
155 |
year={2023},
|
156 |
eprint={2305.04928},
|
|
|
30 |
|
31 |
This model was created during the research collaboration between Bayer Pharma and The Institute for Artificial Intelligence Research and Development of Serbia.
|
32 |
The model is trained on 26 biomedical Named Entity (NE) classes and can perform zero-shot inference. It also can be further fine-tuned for new classes with just few examples (few-shot learning).
|
33 |
+
For more details about our method please see the paper named ["From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts"](https://arxiv.org/abs/2305.04928). The model corresponds to PubMedBERT-based model, trained with 1 in the first segment (check paper for more details).
|
34 |
|
35 |
Model takes two strings as input. String1 is NE label that is being searched in second string. String2 is short text where one wants to searc for NE (represented by String1).
|
36 |
Model outputs list of ones (corresponding to the found Named Entities) and zeros (corresponding to other non-NE tokens) of the Sring2.
|
|
|
145 |
|
146 |
If you use this model, or are inspired by it, please cite in your paper the following paper:
|
147 |
|
148 |
+
Košprdić M.,Prodanović N., Ljajić A., Bašaragin B., Milošević N., 2023. From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts. arXiv preprint arXiv:2305.04928. https://arxiv.org/abs/2305.04928
|
149 |
|
150 |
or in bibtex:
|
151 |
```
|
152 |
@misc{kosprdic2023transformerbased,
|
153 |
+
title={From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts},
|
154 |
author={Miloš Košprdić and Nikola Prodanović and Adela Ljajić and Bojana Bašaragin and Nikola Milošević},
|
155 |
year={2023},
|
156 |
eprint={2305.04928},
|