Richard Brath

Richard Brath, Daniel Keim, Johannes Knittel et al.

With a constant increase of learned parameters, modern neural language models become increasingly more powerful. Yet, explaining these complex model's behavior remains a widely unsolved problem. In this paper, we discuss the role interactive visualization can play in explaining NLP models (XNLP). We motivate the use of visualization in relation to target users and common NLP pipelines. We also present several use cases to provide concrete examples on XNLP with visualization. Finally, we point out an extensive list of research opportunities in this field.

Richard Brath

There are still many potential literature visualizations to be discovered. By focusing on a single text, the author surveys many existing visualizations across research domains, in the wild, and creates new visualizations. 58 techniques are indicated, suggesting a wider variety of visualizations beyond research disciplines.

Richard Brath

Digital humanities are rooted in text analysis. However, most visualization paradigms use only categoric, ordered or quantitative data. Literal text must be considered a base data type to encode into visualizations. Literal text offers functional, perceptual, cognitive, semantic and operational benefits. These are briefly illustrated with a subset of sample visualizations focused on semantic word sequences, indicating benefits over standard graphs, maps, treemaps, bar charts and narrative layouts.