You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
AI2 ImpACT License – Low Risk Artifacts (LR Agreement) https://allenai.org/impact-license
Log in or Sign Up to review the conditions and access this model content.
Field of study pytorch model is a finetuned version of allenai/scibert_scivocab_uncased.
Data for finetuning was harvested utlizing OpenAI models using following prompt:
def prompt_with_journal(title, abstract, journal_name):
message = [
{"role": "system", "content": "You are a highly intelligent and accurate information extraction system. You take title, abstract, journal name of a \
scientific article as input and your task is to classify the scientific field of study of the passage.",
"role": "user", "content": "You need to classify it with key: 'field_of_study' assign as many 'field_of_study' as you find it fit: \
'Agricultural and Food sciences', \
'Art', \
'Biology',\
'Business',\
'Chemistry',\
'Computer science',\
'Economics',\
'Education',\
'Engineering',\
'Environmental science',\
'Geography',\
'Geology',\
'History',\
'Law',\
'Linguistics',\
'Materials science',\
'Mathematics',\
'Medicine',\
'Philosophy',\
'Physics',\
'Political science',\
'Psychology',\
'Sociology'\
Only select from the above list, or 'Other'."},
{"role": "assistant",
"content": ("```python \n"
f"title = { title } \n"
f"abstract = { abstract }\n"
f"journal_name = { journal_name }\n"
"{'field_of_study': ["
)},]
return message
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.