TIGER-AI-Lab/KB-BINDER

"Few-shot In-context Learning for Knowledge Base Question Answering" [ACL2023]

37
/ 100
Emerging

This tool helps AI engineers build and evaluate systems that answer complex questions using a knowledge base, even with limited training examples. You provide a knowledge base (like Freebase) and a small set of example questions and answers. The system then generates accurate answers to new, similar questions by querying the knowledge base. It's designed for machine learning engineers and researchers working on natural language understanding.

No commits in the last 6 months.

Use this if you are a machine learning engineer working on question-answering systems and need to quickly adapt a model to a new knowledge base with very few labeled examples.

Not ideal if you are looking for an off-the-shelf solution for end-users or do not have the technical expertise to set up a knowledge base server and run Python scripts.

knowledge-base-querying few-shot-learning natural-language-processing question-answering machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

66

Forks

8

Language

Python

License

MIT

Last pushed

Jan 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/TIGER-AI-Lab/KB-BINDER"

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