Visualization Techniques to Enhance Automated Event Extraction

TL;DR

This paper explores visualization techniques that improve understanding and analysis of complex, high-dimensional text data in automated event extraction, aiding various stages from data exploration to validation.

Contribution

It introduces visualization methods tailored for NLP event extraction tasks, demonstrating their effectiveness across multiple analysis stages in a case study.

Findings

Visualizations facilitate exploratory data analysis

They assist in machine learning training diagnostics

They support post-inference validation

Abstract

Robust visualization of complex data is critical for the effective use of NLP for event classification, as the volume of data is large and the high-dimensional structure of text makes data challenging to summarize succinctly. In event extraction tasks in particular, visualization can aid in understanding and illustrating the textual relationships from which machine learning tools produce insights. Through our case study which seeks to identify potential triggers of state-led mass killings from news articles using NLP, we demonstrate how visualizations can aid in each stage, from exploratory analysis of raw data, to machine learning training analysis, and finally post-inference validation.