megagonlabs/zett

:see_no_evil: Code for Zero-shot Triplet Extraction by Template Infilling (Kim et al; IJCNLP-AACL 2023)

22
/ 100
Experimental

This project helps data scientists or researchers automatically extract specific relationships (triplets like "person works at company") from unstructured text, even for relationship types it hasn't seen before. You provide raw text documents, and it identifies and pulls out these structured facts. It's designed for natural language processing specialists working with large text corpora.

No commits in the last 6 months.

Use this if you need to extract structured facts from text for many relationship types, including novel ones, without needing to manually label extensive training data for each new type.

Not ideal if your primary goal is simple keyword extraction or if you only work with a very small, fixed set of known relationship types that can be easily hard-coded or mapped.

natural-language-processing information-extraction text-analytics knowledge-graph-construction data-mining
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

21

Forks

Language

Python

License

BSD-3-Clause

Last pushed

Feb 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/megagonlabs/zett"

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