Probabilistic Reasoning via Deep Learning: Neural Association Models
Probabilistic Reasoning via Deep Learning: Neural Association Models
复制标题
DOI：
--
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
QUAN LIU;Hui Jiang;Zhenhua Ling;Si Wei;Yu Hu
中科院分区：
文献类型：
--
作者：
QUAN LIU;Hui Jiang;Zhenhua Ling;Si Wei;Yu Hu
在本文中，我们提出一种新的深度学习方法，称为神经关联模型（NAM），用于人工智能中的概率推理。我们建议使用神经网络来模拟一个领域中任意两个事件之间的关联。神经网络将一个事件作为输入，并计算另一个事件的条件概率，以模拟这两个事件相关联的可能性。条件概率的实际含义因应用程序而异，并取决于模型的训练方式。在这项工作中，作为两个案例研究，我们研究了两种NAM结构，即深度神经网络（DNN）和关系调制神经网络（RMNN），用于人工智能中的几个概率推理任务，包括识别文本蕴涵，多关系知识库中的三重分类和常识推理。来自WordNet， FreeBase和ConceptNet的几个流行数据集的实验结果都表明，dnn和rmnn的表现同样好，并且它们可以显著优于这些推理任务的传统方法。此外，与深度神经网络相比，rmnn在知识转移方面具有优势，其中预训练模型可以在只观察少量训练样本后快速扩展到不可见的关系。为了进一步证明所提出模型的有效性，在这项工作中，我们将NAMs应用于解决具有挑战性的Winograd Schema （WS）问题。在一组WS问题上进行的实验证明，所提出的模型具有常识推理的潜力。
In this paper, we propose a new deep learning approach, called neural association model (NAM), for probabilistic reasoning in artificial intelligence. We propose to use neural networks to model association between any two events in a domain. Neural networks take one event as input and compute a conditional probability of the other event to model how likely these two events are to be associated. The actual meaning of the conditional probabilities varies between applications and depends on how the models are trained. In this work, as two case studies, we have investigated two NAM structures, namely deep neural networks (DNN) and relation-modulated neural nets (RMNN), on several probabilistic reasoning tasks in AI, including recognizing textual entailment, triple classification in multi-relational knowledge bases and commonsense reasoning. Experimental results on several popular datasets derived from WordNet, FreeBase and ConceptNet have all demonstrated that both DNNs and RMNNs perform equally well and they can significantly outperform the conventional methods available for these reasoning tasks. Moreover, compared with DNNs, RMNNs are superior in knowledge transfer, where a pre-trained model can be quickly extended to an unseen relation after observing only a few training samples. To further prove the effectiveness of the proposed models, in this work, we have applied NAMs to solving challenging Winograd Schema (WS) problems. Experiments conducted on a set of WS problems prove that the proposed models have the potential for commonsense reasoning.