Comprehension Based Question Answering using Bloom's Taxonomy

TL;DR

This paper applies Bloom's Taxonomy to enhance the comprehension abilities of large pre-trained language models in zero-shot question answering by providing targeted context, resulting in improved performance on common sense datasets.

Contribution

It introduces a novel method of using Bloom's Taxonomy to generate relevant context that improves zero-shot question answering in language models.

Findings

Targeted context improves model accuracy

Performance gains observed across multiple datasets

Bloom's Taxonomy effectively guides context selection

Abstract

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.