Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects
Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects
复制标题
DOI：
10.18653/v1/d18-1288
复制
发表时间：
2018
期刊：
影响因子：
3.9
通讯作者：
Cory Shain;William Schuler
中科院分区：
文献类型：
--
作者：
Cory Shain;William Schuler
计算心理语言学的研究人员经常使用线性模型来研究人类受试者产生的时间序列数据。然而，时间序列可能通过时间扩散违反这些模型的假设，其中刺激呈现对实验其余部分的反应具有挥之不去的影响。本文提出了一种新的统计模型，该模型借鉴了数字信号处理，通过将预测器和响应重铸为卷积相关信号，利用机器学习的最新进展来拟合任意形状的潜在脉冲响应函数（irf）。一项综合实验显示成功地恢复了真正的潜在irf，心理语言学实验揭示了潜在时间动态的可信、可复制和细粒度估计，具有与广泛使用的替代方法相当或改进的预测质量。
Researchers in computational psycholinguistics frequently use linear models to study time series data generated by human subjects. However, time series may violate the assumptions of these models through temporal diffusion, where stimulus presentation has a lingering influence on the response as the rest of the experiment unfolds. This paper proposes a new statistical model that borrows from digital signal processing by recasting the predictors and response as convolutionally-related signals, using recent advances in machine learning to fit latent impulse response functions (IRFs) of arbitrary shape. A synthetic experiment shows successful recovery of true latent IRFs, and psycholinguistic experiments reveal plausible, replicable, and fine-grained estimates of latent temporal dynamics, with comparable or improved prediction quality to widely-used alternatives.