DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning
This library addresses the need for easier integration of symbolic and sub-symbolic models in deep learning, particularly for researchers and practitioners working on NLP and other tasks, though it is incremental as it builds on existing approaches.
The authors tackled the problem of integrating symbolic domain knowledge into deep learning models by developing DomiKnowS, a library that simplifies programming for such integration and improves model explainability, performance, and generalizability in low-data regimes.
We demonstrate a library for the integration of domain knowledge in deep learning architectures. Using this library, the structure of the data is expressed symbolically via graph declarations and the logical constraints over outputs or latent variables can be seamlessly added to the deep models. The domain knowledge can be defined explicitly, which improves the models' explainability in addition to the performance and generalizability in the low-data regime. Several approaches for such an integration of symbolic and sub-symbolic models have been introduced; however, there is no library to facilitate the programming for such an integration in a generic way while various underlying algorithms can be used. Our library aims to simplify programming for such an integration in both training and inference phases while separating the knowledge representation from learning algorithms. We showcase various NLP benchmark tasks and beyond. The framework is publicly available at Github(https://github.com/HLR/DomiKnowS).