Modeling Content and Context with Deep Relational Learning
This work addresses the problem of combining neural and symbolic methods for NLP practitioners, but it appears incremental as it builds on existing neural-symbolic frameworks.
The authors tackled the challenge of modeling long texts and structural dependencies in NLP by introducing DRaiL, an open-source declarative framework for deep relational models, which supports integration with language encoders and studies interactions between representation, inference, and learning.
Building models for realistic natural language tasks requires dealing with long texts and accounting for complicated structural dependencies. Neural-symbolic representations have emerged as a way to combine the reasoning capabilities of symbolic methods, with the expressiveness of neural networks. However, most of the existing frameworks for combining neural and symbolic representations have been designed for classic relational learning tasks that work over a universe of symbolic entities and relations. In this paper, we present DRaiL, an open-source declarative framework for specifying deep relational models, designed to support a variety of NLP scenarios. Our framework supports easy integration with expressive language encoders, and provides an interface to study the interactions between representation, inference and learning.