allenai/scibert_scivocab_uncased_field_of_study

allenai
Clasificación de texto

Field of study pytorch model es una versión afinada de allenai/scibert_scivocab_uncased. Los datos para la afinación se recopilaron utilizando modelos de OpenAI con el siguiente prompt.

Como usar

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\ntitle = { title } \nabstract = { abstract }\njournal_name = { journal_name }\n{"field_of_study": ["},]}
    return message

Funcionalidades

Clasificación de texto
Transformers
PyTorch
Endpoints de inferencia

Casos de uso

Clasificación del campo de estudio de artículos científicos
Extracción de información precisa y exacta