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 1608.05604cs.CL
收藏

基于神经注意力的人类阅读建模

Modeling Human Reading with Neural Attention

University of Edinburgh(爱丁堡大学)

Michael Hahn, Frank Keller

摘要:

当人类阅读文本时,他们会固定一些单词并跳过其他单词。然而,很少有人尝试用计算模型来解释跳跃行为,因为大多数现有的工作都集中在预测阅读时间(例如,~使用NaHCO 3)。在本文中,我们提出了一种新的方法,模型跳过和阅读,使用一个无监督的架构,结合了神经注意力与自动编码,训练的原始文本使用强化学习。我们的模型将人类阅读行为解释为语言理解的精确性(准确地编码输入)和注意力的经济性(尽可能少地固定单词)之间的权衡。我们评估模型的邓迪眼动跟踪语料库,表明它准确地预测跳过行为和阅读时间,是有竞争力的,并捕捉已知的定性特征的人类阅读。

英文摘要:

When humans read text, they fixate some words and skip others. However, there have been few attempts to explain skipping behavior with computational models, as most existing work has focused on predicting reading times (e.g.,~using surprisal). In this paper, we propose a novel approach that models both skipping and reading, using an unsupervised architecture that combines a neural attention with autoencoding, trained on raw text using reinforcement learning. Our model explains human reading behavior as a tradeoff between precision of language understanding (encoding the input accurately) and economy of attention (fixating as few words as possible). We evaluate the model on the Dundee eye-tracking corpus, showing that it accurately predicts skipping behavior and reading times, is competitive with surprisal, and captures known qualitative features of human reading.

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。

↑