yuzhimanhua/MICoL

Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification (WWW'22)

38
/ 100
Emerging

This project helps researchers and academics categorize scientific papers quickly and accurately, even for new topics they haven't seen before. It takes a paper's text and its associated metadata (like authors, venue, references) and outputs a list of relevant subject labels. This is ideal for scientists, librarians, or information managers who need to organize large collections of academic literature.

No commits in the last 6 months.

Use this if you need to automatically assign subject categories to a large volume of scientific papers, especially when dealing with topics that may not have many previously labeled examples.

Not ideal if your classification task does not involve rich metadata (authors, citations, venues) or if you are working with non-academic text.

academic-research scientific-document-classification literature-management zero-shot-learning information-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

32

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Jun 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yuzhimanhua/MICoL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.