Text Simplification for Comprehension-based Question-Answering

Abstract

Text simplification is the process of splitting and rephrasing a sentence to a sequence of sentences making it easier to read and understand while preserving the content and approximating the original meaning. Text simplification has been exploited in NLP applications like machine translation, summarization, semantic role labeling, and information extraction, opening a broad avenue for its exploitation in comprehension-based questionanswering downstream tasks. In this work, we investigate the effect of text simplification in the task of question-answering using a comprehension context. We release Simple-SQuAD, a simplified version of the widely-used SQuAD dataset.Firstly, we outline each step in the dataset creation pipeline, including style transfer, thresholding of sentences showing correct transfer, and offset finding for each answer. Secondly, we verify the quality of the transferred sentences through various methodologies involving both automated and human evaluation. Thirdly, we benchmark the newly created corpus and perform an ablation study for examining the effect of the simplification process in the SQuAD-based question answering task. Our experiments show that simplification leads to up to 2.04% and 1.74% increase in Exact Match and F1, respectively. Finally, we conclude with an analysis of the transfer process, investigating the types of edits made by the model, and the effect of sentence length on the transfer model.

Can Knowledge Graphs Simplify Text?

“…The primary objective of TS is to propagate information to a more expansive audience, including individuals with lower literacy levels [47], those with reading disabilities [7], nonnative speakers [37], and individuals lacking specialized knowledge within specific domains, such as medically related documents [1,52]. Therefore it can also enhance various natural language processing (NLP) tasks that necessitate less complex texts for optimal results, including question answering [10], information extraction [51], and machine translation [48].…”