sebischair/FusionSent
Repository of the ICNLSP 2024 paper "Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes"
This project helps researchers and librarians automatically categorize scientific papers, articles, or other long-form documents. You input the text of a document (like a title and abstract) and it outputs the relevant scientific categories, even if you only have a few examples for each category. This is ideal for academics, research institutions, and digital libraries managing large collections of scientific literature.
No commits in the last 6 months. Available on PyPI.
Use this if you need to accurately assign multiple subject categories to scientific documents, especially when you have many different categories and limited labeled examples for each.
Not ideal if your documents are not scientific or if you have a vast amount of labeled data for every single category.
Stars
17
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 07, 2025
Commits (30d)
0
Dependencies
51
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/sebischair/FusionSent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/setfit
Efficient few-shot learning with Sentence Transformers
YujiaBao/Distributional-Signatures
"Few-shot Text Classification with Distributional Signatures" ICLR 2020
zhongyuchen/few-shot-text-classification
Few-shot binary text classification with Induction Networks and Word2Vec weights initialization
ELM-Research/ECG-Language-Models
A Training and Evaluation Framework for ECG-Language Models (ELMs)
StefanHeng/ECG-Representation-Learning
Self-supervised pre-training for ECG representation with inspiration from transformers & computer vision