The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference
This addresses the challenge of model interpretability for NLP researchers and practitioners, but it is incremental as it reviews and motivates existing approaches rather than introducing new methods.
The paper tackles the problem of explaining complex neural language models by discussing the role of interactive visualization in NLP, providing use cases and research opportunities without presenting specific results or numbers.
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.