yuzhimanhua/MATCH

MATCH: Metadata-Aware Text Classification in A Large Hierarchy (WWW'21)

43
/ 100
Emerging

This project helps researchers, librarians, and information scientists automatically categorize academic papers and medical articles into detailed, hierarchical subject areas. It takes the full text of articles, along with metadata like authors, venues, and references, and outputs a list of relevant subject labels organized in a taxonomy. It's designed for anyone needing to accurately classify large volumes of text in scientific or medical domains.

117 stars. No commits in the last 6 months.

Use this if you need to automatically assign fine-grained, structured categories to scientific papers or medical articles, leveraging not just the content but also contextual information about the document.

Not ideal if your classification task involves a flat list of categories, doesn't benefit from metadata like authors or references, or if you're working outside academic or medical research domains.

academic-research medical-informatics taxonomy-management document-classification knowledge-organization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

117

Forks

18

Language

Python

License

Apache-2.0

Last pushed

Apr 02, 2024

Commits (30d)

0

Get this data via API

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

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