phosseini/causal-reasoning

Knowledge-Augmented Language Models for Cause-Effect Relation Classification https://arxiv.org/abs/2112.08615

27
/ 100
Experimental

This project helps researchers and data scientists improve how language models understand cause-and-effect relationships from text. It takes structured knowledge graphs like ATOMIC2020 or GLUCOSE, converts them into natural language sentences, and then uses these sentences to further train language models like BERT or RoBERTa. The outcome is a language model better equipped to identify causal links in new text, useful for those working with large text datasets to extract insights.

No commits in the last 6 months.

Use this if you are a researcher or data scientist needing to enhance a language model's ability to accurately classify cause-effect relationships within text for tasks like logical reasoning or predictive analytics.

Not ideal if you are looking for a plug-and-play solution for general text classification without a specific focus on causal inference or if you lack expertise in training and fine-tuning large language models.

natural-language-processing causal-inference knowledge-graph-verbalization text-understanding machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Python

License

Last pushed

Jun 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/phosseini/causal-reasoning"

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