From Unstructured Text to Causal Knowledge Graphs: A Transformer-Based Approach
This work addresses the need for cognitive systems in domains like scientific discovery and social science to process causal knowledge from text, though it is incremental as it applies existing transformer methods to a specific extraction task.
The paper tackles the problem of extracting diverse causal relationships from unstructured text to build knowledge graphs, presenting a transformer-based NLP architecture that accurately extracts variables, causal relationships, qualifiers, and word senses, with promising results demonstrated in use cases involving academic publications, news articles, and social media.
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.