Meta Sequence Learning for Generating Adequate Question-Answer Pairs

TL;DR

This paper introduces MetaQA, a novel learning scheme that uses meta-sequence representations of sentences to generate high-quality question-answer pairs for reading comprehension assessments, demonstrating high accuracy on SAT tests.

Contribution

MetaQA is a new method that learns to generate question-answer pairs from meta-sequences of sentences, improving efficiency and accuracy in automatic question generation.

Findings

Achieves over 97% accuracy in generating QAPs

Generates large numbers of syntactically and semantically correct QAPs

Operates efficiently on small training datasets

Abstract

Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) on the main points of the document. We present a learning scheme to generate adequate QAPs via meta-sequence representations of sentences. A meta sequence is a sequence of vectors comprising semantic and syntactic tags. In particular, we devise a scheme called MetaQA to learn meta sequences from training data to form pairs of a meta sequence for a declarative sentence (MD) and a corresponding interrogative sentence (MIs). On a given declarative sentence, a trained MetaQA model converts it to a meta sequence, finds a matched MD, and uses the corresponding MIs and the input sentence to generate QAPs. We implement MetaQA for the English language using semantic-role labeling, part-of-speech tagging, and named-entity recognition, and show that trained on a small dataset, MetaQA generates efficiently over the official SAT practice reading tests a large number of syntactically and semantically correct QAPs with over 97\% accuracy.