Comprehension Based Question Answering using Bloom's Taxonomy
This work addresses the challenge of enhancing model comprehension for question answering tasks, though it is incremental as it builds on existing methods with a novel application of an educational framework.
The paper tackled the problem of limited knowledge utilization in pre-trained language models by applying Bloom's Taxonomy to improve comprehension skills in zero-shot question answering, resulting in performance improvements across four common sense datasets.
Current pre-trained language models have lots of knowledge, but a more limited ability to use that knowledge. Bloom's Taxonomy helps educators teach children how to use knowledge by categorizing comprehension skills, so we use it to analyze and improve the comprehension skills of large pre-trained language models. Our experiments focus on zero-shot question answering, using the taxonomy to provide proximal context that helps the model answer questions by being relevant to those questions. We show targeting context in this manner improves performance across 4 popular common sense question answer datasets.