Home

causalatee is a Python library to simplify handling causality in natural language: extraction, training extraction models, unified datasets, and storing/querying results as causal graphs.

Installation

pip install causalatee

Where to go from here

• Tasks — the three standardized tasks (Detection, Candidate Extraction, Identification) that every dataset and model interface below shares.
• Datasets — causality corpora, converted into one consistent HuggingFace-compatible schema.
• Models — model approaches for the tasks above, from rule-based baselines to fine-tuned neural classifiers, all satisfying the same batch-callable causalatee.models Protocol interfaces.
• Causal Graphs — storing and querying causal relations as a graph, with several interchangeable backends (CauseNet, CGF, SQLGraph, ...).
• Examples — runnable notebooks covering fine-tuning, baselines, and building/mining a causal graph.
• API Reference — the full causalatee API.