ActKnow: Active External Knowledge Infusion Learning for Question Answering in Low Data Regime
This addresses the challenge of low data availability in practical NLP applications, particularly for question answering, though it is an incremental improvement over existing few-shot learning techniques.
The paper tackles the problem of training deep learning models for question answering with limited data by actively infusing external knowledge from knowledge graphs like Concept-Net, resulting in a 4% accuracy improvement on benchmarks such as ARC-challenge and OpenBookQA when using only 20% of training examples.
Deep learning models have set benchmark results in various Natural Language Processing tasks. However, these models require an enormous amount of training data, which is infeasible in many practical problems. While various techniques like domain adaptation, fewshot learning techniques address this problem, we introduce a new technique of actively infusing external knowledge into learning to solve low data regime problems. We propose a technique called ActKnow that actively infuses knowledge from Knowledge Graphs (KG) based "on-demand" into learning for Question Answering (QA). By infusing world knowledge from Concept-Net, we show significant improvements on the ARC Challenge-set benchmark over purely text-based transformer models like RoBERTa in the low data regime. For example, by using only 20% training examples, we demonstrate a 4% improvement in the accuracy for both ARC-challenge and OpenBookQA, respectively.