Neural Query Language: A Knowledge Base Query Language for Tensorflow
This addresses the problem of integrating knowledge bases into AI systems for researchers and practitioners, representing a novel method rather than an incremental improvement.
The paper tackles the difficulty of integrating large knowledge bases into gradient-based learning systems by introducing a framework that allows access to soft symbolic databases using only differentiable operators, enabling neural models to adjust fact confidences, incorporate prior knowledge, and learn query templates from text, with demonstrated scalability to millions of tuples and hundreds of thousands of entities on a single GPU.
Large knowledge bases (KBs) are useful for many AI tasks, but are difficult to integrate into modern gradient-based learning systems. Here we describe a framework for accessing soft symbolic database using only differentiable operators. For example, this framework makes it easy to conveniently write neural models that adjust confidences associated with facts in a soft KB; incorporate prior knowledge in the form of hand-coded KB access rules; or learn to instantiate query templates using information extracted from text. NQL can work well with KBs with millions of tuples and hundreds of thousands of entities on a single GPU.