Augmenting Neural Networks with First-order Logic
Augmenting Neural Networks with First-order Logic
复制标题
DOI：
10.18653/v1/p19-1028
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Tao Li;Vivek Srikumar
中科院分区：
文献类型：
--
作者：
Tao Li;Vivek Srikumar
今天，训练神经网络的主要范式涉及在大型数据集上最大限度地减少任务损失。使用世界知识为模型提供信息，同时保持执行端到端培训的能力仍然是一个悬而未决的问题。在本文中，我们提出了一种新的框架，用于将声明性知识引入神经网络架构，以指导训练和预测。我们的框架系统地将逻辑语句编译成计算图，以增强神经网络，而无需额外的可学习参数或手动重新设计。我们评估我们的建模策略上的三个任务：机器理解，自然语言推理和文本组块。我们的实验表明，知识增强网络可以大大提高基线，特别是在低数据的制度。
Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction. Our framework systematically compiles logical statements into computation graphs that augment a neural network without extra learnable parameters or manual redesign. We evaluate our modeling strategy on three tasks: machine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.