megagonlabs/zett
:see_no_evil: Code for Zero-shot Triplet Extraction by Template Infilling (Kim et al; IJCNLP-AACL 2023)
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.
Stars
21
Forks
—
Language
Python
License
BSD-3-Clause
Category
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.
Higher-rated alternatives
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...