Explainability, Interpretability & Transparency in NLP

Explainability, Interpretability & Transparency (XAI) in NLP is a subfield of Responsible NLP that deals with developing algorithms and models that can provide transparent and interpretable predictions, and explain the reasoning and decision-making processes behind them. It involves developing techniques that can generate human-readable explanations, highlight important features and patterns, and enable users to interact and refine the models.

Synonyms:

XAI, Explainable Natural Language Processing, EXNLP

Papers published in this field over the years:

Hierarchy

Publications for Explainability, Interpretability & Transparency in NLP

Sort by

Showing results 1 to 0 of 0

Researchers for Explainability, Interpretability & Transparency in NLP

Sort by