Neural Particle Smoothing for Sampling from Conditional Sequence Models
Neural Particle Smoothing for Sampling from Conditional Sequence Models
复制标题
DOI：
10.18653/v1/n18-1085
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Chu-Cheng Lin;Jason Eisner
中科院分区：
文献类型：
--
作者：
Chu-Cheng Lin;Jason Eisner
我们引入神经粒子平滑，一个顺序的蒙特卡罗方法从一个给定的概率模型的输入字符串的采样注释。与传统的粒子滤波算法相比，我们通过从右到左的LSTM训练了一个预测输入字符串结尾的建议分布。我们证明，这种创新可以提高样品的质量。为了激励我们的正式选择，我们解释了神经转导模型和我们的采样器如何可以被视为低维但非线性的近似，在非常大的状态空间上与Hysteresis一起工作。
We introduce neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model. In contrast to conventional particle filtering algorithms, we train a proposal distribution that looks ahead to the end of the input string by means of a right-to-left LSTM. We demonstrate that this innovation can improve the quality of the sample. To motivate our formal choices, we explain how neural transduction models and our sampler can be viewed as low-dimensional but nonlinear approximations to working with HMMs over very large state spaces.