GLUECons: A Generic Benchmark for Learning Under Constraints
This provides a framework for systematic comparison of constraint integration techniques, facilitating research to address issues in state-of-the-art neural models, though it is incremental as it builds on existing knowledge integration approaches.
The authors tackled the lack of a standardized benchmark for evaluating methods that integrate domain knowledge as constraints into deep learning, by creating GLUECons, a collection of nine NLP and vision tasks with specified constraint sources and implemented models, reporting results using extended evaluation criteria.
Recent research has shown that integrating domain knowledge into deep learning architectures is effective -- it helps reduce the amount of required data, improves the accuracy of the models' decisions, and improves the interpretability of models. However, the research community is missing a convened benchmark for systematically evaluating knowledge integration methods. In this work, we create a benchmark that is a collection of nine tasks in the domains of natural language processing and computer vision. In all cases, we model external knowledge as constraints, specify the sources of the constraints for each task, and implement various models that use these constraints. We report the results of these models using a new set of extended evaluation criteria in addition to the task performances for a more in-depth analysis. This effort provides a framework for a more comprehensive and systematic comparison of constraint integration techniques and for identifying related research challenges. It will facilitate further research for alleviating some problems of state-of-the-art neural models.