Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
This addresses knowledge gaps in science entailment tasks, but it is incremental as it builds on existing neural methods with a knowledge lookup module.
The paper tackled the problem of knowledge gaps in textual entailment by integrating a structured knowledge base with neural models, resulting in a 5% improvement over the base model on the SciTail dataset.
Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.