SGCM: Salience-Guided Context Modeling for Question Generation

Abstract

We tackle Paragraph-level Question Generation (abbr., PQG) in this paper. PQG is a task of automatically generating questions given paragraphs and answers. Identifying the relevant sentences to answers is crucial for reasoning the possible questions before generation. Accordingly, we propose a salience-guided approach to enhance PQG. Specifically, we construct an auxiliary task of identifying salient sentences that manifest relevance. Grounded on this auxiliary task and the main task of PQG, we strengthen the BART encoder during training within a multitask learning framework. In particular, we utilize the identified salient sentences as an explicit guidance to enable the salience-aware attention computation in the BART decoder. We experiment on the benchmark dataset FairytaleQA. The test results show that our approach yields substantial improvements compared to the BART baseline, achieving the Rouge-L, BLEU4, BERTScore, Q-BLUE-3 and F1-scores of about 56.56%, 19.78%, 61.19%, 54.33% and 43.55%, respectively. Both the source codes and models will be publicly available.