2019/09/24 by Shikhar Vashishth, Shyam Upadhyay, Vashishth, Shikhar +5 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.1909.11218
arxiv created 2019/09/24 · openalex publication_date 2019/09/24 · arxiv updated 2019/09/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the interpretability of attention weights (Jain & Wallace, 2019; Vig & Belinkov, 2019). Amid such confusion arises the need to understand attention mechanism more systematically. In this work, we attempt to fill this gap by giving a comprehensive explanation which justifies both kinds of observations (i.e., when is attention interpretable and when it is not). Through a series of experiments on diverse NLP tasks, we validate our observations and reinforce our claim of interpretability of attention through manual evaluation.