Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering (ODQA) systems. However, current AC approaches require tuning of all model parameters, and training state-of-the-art ODQA models requires significant computational resources that may not be available for most researchers. We propose Adaptive Passage Encoder, an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU. It keeps the parameters of the base ODQA model fixed, but it overrides the default layer-by-layer computation of the encoder with an AC policy that is trained to optimise the computational efficiency of the model. Our experimental results show that our method improves upon a state-of-the-art model on two datasets, and is also more accurate than previous AC methods due to the stronger base ODQA model. All source code and datasets are available at https://github.com/uclnlp/APE.
翻译:事实证明,适应性计算(AC)在提高开放域问答(ODQA)系统的效率方面是有效的,然而,目前的 AC 方法需要调整所有模型参数,培训最先进的 ODQA 模型需要大量计算资源,而大多数研究人员可能得不到这种资源。我们提议了适应性被动编码器,这种AC 方法可以适用于现有的ODQA模型,并且可以在单一的GPU上得到有效培训。它保持了ODQA模型的参数固定,但它取代了对编码器的默认逐层计算,而AC 政策受过培训,可以优化模型的计算效率。我们的实验结果表明,我们的方法在两种数据集的状态先进模型上有所改进,并且由于更强大的ODQA模型,也比以前A C 方法更加精确。所有源代码和数据集都可在https://github.com/uclnp/APE查阅。