Research Area:  Machine Learning

Abstract:

The attention layer in a neural network model provides insights into the models 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.

Keywords:  

Author(s) Name:  Shikhar Vashishth, Shyam Upadhyay, Gaurav Singh Tomar, Manaal Faruqui

Publisher name:  arXiv

DOI:  10.48550/arXiv.1909.11218

Volume Information:  Volume 2019

Paper Link:   https://arxiv.org/abs/1909.11218