DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning

Abstract

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 explainability of the models in addition to their performance and generalizability in the lowdata regime. Several approaches for such integration of symbolic and sub-symbolic models have been introduced; however, there is no library to facilitate the programming for such integration in a generic way while various underlying algorithms can be used. Our library aims to simplify programming for such 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 1 .

Lazy-k Decoding: Constrained Decoding for Information Extraction

“…4, we make no further assumption about the constraint. This is important because many existing constrained decoding approaches require the constraints to be expressed in linear form (Faghihi et al, 2023). Some problems may consist of both linear and non-linear constraints.…”