|
|
--- |
|
|
widget: |
|
|
- text: >- |
|
|
The third is the path length between long-range dependencies in the |
|
|
network. |
|
|
example_title: Intent Classify |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
This model is finetuned SciBERT model for context classification in scientific journals. |
|
|
The model classifies intentions of the scientific text, based on the topic of their description. |
|
|
It categorizes if the context explains the background, result or method of the paper. |
|
|
The output classes based on the text are as follows: |
|
|
</br> |
|
|
Text describing related work, introduction and uses are classified as <b>background</b> |
|
|
Methods and implementation details are classified as <b>method</b> |
|
|
Results and analysis are classified as <b>result</b> |
|
|
|
|
|
For finetuning, I have used dataset from Cohan et al. https://aclanthology.org/N19-1361.pdf |
