SemPool: Simple, robust, and interpretable KG pooling for enhancing language models

Knowledge Graph (KG) powered question answering (QA) performs complex reasoning over language semantics as well as knowledge facts. Graph Neural Networks (GNNs) learn to aggregate information from the underlying KG, which is combined with Language Models (LMs) for effective reasoning with the given question. However, GNN-based methods for QA rely on the graph information of the candidate answer nodes, which limits their effectiveness in more challenging settings where critical answer information is not included in the KG. We propose a …

cs.cl facts gnn gnns graph graph neural networks information knowledge knowledge graph language language models learn lms networks neural networks pooling question question answering reasoning robust semantics simple