Attention in Reasoning: Dataset, Analysis, and Modeling
This work addresses the need for more interpretable and effective attention mechanisms in AI, particularly for visual question answering, but it is incremental as it builds on existing attention methods with new supervision techniques.
The authors tackled the problem of evaluating and improving attention mechanisms in neural networks by proposing the AiR framework, which introduces a metric based on atomic reasoning operations and uses human eye-tracking data to analyze and supervise attention, resulting in enhanced reasoning capability and task performance in visual question answering models.
While attention has been an increasingly popular component in deep neural networks to both interpret and boost the performance of models, little work has examined how attention progresses to accomplish a task and whether it is reasonable. In this work, we propose an Attention with Reasoning capability (AiR) framework that uses attention to understand and improve the process leading to task outcomes. We first define an evaluation metric based on a sequence of atomic reasoning operations, enabling a quantitative measurement of attention that considers the reasoning process. We then collect human eye-tracking and answer correctness data, and analyze various machine and human attention mechanisms on their reasoning capability and how they impact task performance. To improve the attention and reasoning ability of visual question answering models, we propose to supervise the learning of attention progressively along the reasoning process and to differentiate the correct and incorrect attention patterns. We demonstrate the effectiveness of the proposed framework in analyzing and modeling attention with better reasoning capability and task performance. The code and data are available at https://github.com/szzexpoi/AiR