CATE: CAusality Tree Extractor from Natural Language Requirements

TL;DR

CATE is a tool that automatically extracts and visualizes causal relations from natural language requirements as tree structures, aiding in requirements analysis and testing.

Contribution

This paper introduces CATE, a novel method for parsing causal relations into tree structures from natural language requirements, enhancing understanding and automation.

Findings

CATE effectively extracts causal relations with reasonable accuracy.

The tool visualizes causal structures as binary trees.

CATE facilitates better requirements analysis and test case derivation.

Abstract

Causal relations (If A, then B) are prevalent in requirements artifacts. Automatically extracting causal relations from requirements holds great potential for various RE activities (e.g., automatic derivation of suitable test cases). However, we lack an approach capable of extracting causal relations from natural language with reasonable performance. In this paper, we present our tool CATE (CAusality Tree Extractor), which is able to parse the composition of a causal relation as a tree structure. CATE does not only provide an overview of causes and effects in a sentence, but also reveals their semantic coherence by translating the causal relation into a binary tree. We encourage fellow researchers and practitioners to use CATE at https://causalitytreeextractor.com/