From Unstructured Text to Causal Knowledge Graphs: A Transformer-Based Approach

TL;DR

This paper introduces a transformer-based NLP method for extracting detailed causal knowledge graphs from unstructured text, capturing variables, causal relations, qualifiers, and word senses, with promising real-world application results.

Contribution

The paper presents a novel transformer architecture that jointly extracts comprehensive causal knowledge graphs from text, including variables, relations, qualifiers, and senses, advancing the state of the art.

Findings

Accurate extraction of causal relations from diverse text sources

Effective localization of nodes within large ontologies

Promising results in real-world domain applications

Abstract

Qualitative causal relationships compactly express the direction, dependency, temporal constraints, and monotonicity constraints of discrete or continuous interactions in the world. In everyday or academic language, we may express interactions between quantities (e.g., sleep decreases stress), between discrete events or entities (e.g., a protein inhibits another protein's transcription), or between intentional or functional factors (e.g., hospital patients pray to relieve their pain). Extracting and representing these diverse causal relations are critical for cognitive systems that operate in domains spanning from scientific discovery to social science. This paper presents a transformer-based NLP architecture that jointly extracts knowledge graphs including (1) variables or factors described in language, (2) qualitative causal relationships over these variables, (3) qualifiers and magnitudes that constrain these causal relationships, and (4) word senses to localize each extracted node within a large ontology. We do not claim that our transformer-based architecture is itself a cognitive system; however, we provide evidence of its accurate knowledge graph extraction in real-world domains and the practicality of its resulting knowledge graphs for cognitive systems that perform graph-based reasoning. We demonstrate this approach and include promising results in two use cases, processing textual inputs from academic publications, news articles, and social media.