arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.06396cs.CL
收藏

机器阅读理解中人类视觉注意力模型的解释

Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension

University of Stuttgart(斯图加特大学);University of Konstanz(康斯坦茨大学)

Ekta Sood, Simon Tannert, Diego Frassinelli, Andreas Bulling, Ngoc Thang Vu

摘要:

虽然具有注意力机制的神经网络在许多自然语言处理任务上取得了优异的性能,但学习注意力在多大程度上类似于人类视觉注意力仍不清楚。在本文中,我们提出了一种新的方法,利用眼动数据来研究人类视觉注意和神经注意之间的关系,在机器阅读理解。为此,我们引入了一种新的23名参与者的眼动追踪数据集- MQA-RC,其中参与者阅读电影情节并回答预定义的问题。我们比较了基于长短期记忆(LSTM)、卷积神经模型(CNN)和XLNet Transformer架构的最新网络。我们发现,与人类注意力和表现的更高相似性与LSTM和CNN模型显著相关。然而,我们发现这种关系并不适用于XLNet模型-尽管事实上XLNet在这项具有挑战性的任务中表现最好。我们的研究结果表明,不同的架构似乎学习相当不同的神经注意力策略和相似性的神经到人类的注意力并不能保证最佳性能。

英文摘要:

While neural networks with attention mechanisms have achieved superior performance on many natural language processing tasks, it remains unclear to which extent learned attention resembles human visual attention. In this paper, we propose a new method that leverages eye-tracking data to investigate the relationship between human visual attention and neural attention in machine reading comprehension. To this end, we introduce a novel 23 participant eye tracking dataset - MQA-RC, in which participants read movie plots and answered pre-defined questions. We compare state of the art networks based on long short-term memory (LSTM), convolutional neural models (CNN) and XLNet Transformer architectures. We find that higher similarity to human attention and performance significantly correlates to the LSTM and CNN models. However, we show this relationship does not hold true for the XLNet models -- despite the fact that the XLNet performs best on this challenging task. Our results suggest that different architectures seem to learn rather different neural attention strategies and similarity of neural to human attention does not guarantee best performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑