Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
In-BoXBART
|
| 6 |
+
=============
|
| 7 |
+
|
| 8 |
+
An instruction-based unified model for performing various biomedical tasks.
|
| 9 |
+
|
| 10 |
+
You may want to check out
|
| 11 |
+
* Our paper (NAACL 2022 Findings): [In-BoXBART: Get Instructions into Biomedical Multi-Task Learning](https://arxiv.org/abs/2204.07600)
|
| 12 |
+
* GitHub: [Click Here](https://github.com/Mihir3009/In-BoXBART)
|
| 13 |
+
|
| 14 |
+
This work explores the impact of instructional prompts on biomedical Multi-Task Learning. We introduce the BoX, a collection of 32 instruction tasks for Biomedical NLP across (X) various categories. Using this meta-dataset, we propose a unified model termed In-BoXBART, that can jointly learn all tasks of the BoX without any task-specific modules. To the best of our knowledge, this is the first attempt to
|
| 15 |
+
propose a unified model in the biomedical domain and use instructions to achieve generalization across several biomedical tasks.
|
| 16 |
+
|
| 17 |
+
How to Use
|
| 18 |
+
=============
|
| 19 |
+
|
| 20 |
+
You can very easily load the models with Transformers, instead of downloading them manually.
|