During the last years, there has been a lot of interest in achieving some
kind of complex reasoning using deep neural networks. To do that, models like
memory networks (MemNNs) have combined external memory storages and attention
mechanisms. These architectures, however, lack of more c
本文提出了名为神经关联模型(NAM)的新深度学习方法,旨在用于人工智能中的概率推理。作者研究了两种 NAM 结构,即深度神经网络(DNN)和关系调制神经网络(RMNN),并在多个概率推理任务中证明了它们的有效性,包括识别文本蕴含,多关系知识库中的三元分类和常识推理。实验结果表明,这些模型可以显著优于传统的方法,并证明了它们在解决具有挑战性的 Winograd 模式(WS)问题方面的潜力。