Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation

COLING 2022  ·  Zichen Wu, Xin Jia, Fanyi Qu, Yunfang Wu ·

Today the pre-trained language models achieve great success for question generation (QG) task and significantly outperform traditional sequence-to-sequence approaches. However, the pre-trained models treat the input passage as a flat sequence and are thus not aware of the text structure of input passage. For QG task, we model text structure as answer position and syntactic dependency, and propose answer localness modeling and syntactic mask attention to address these limitations. Specially, we present localness modeling with a Gaussian bias to enable the model to focus on answer-surrounded context, and propose a mask attention mechanism to make the syntactic structure of input passage accessible in question generation process. Experiments on SQuAD dataset show that our proposed two modules improve performance over the strong pre-trained model ProphetNet, and combing them together achieves very competitive results with the state-of-the-art pre-trained model.

PDF Abstract COLING 2022 PDF COLING 2022 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Generation SQuAD1.1 ProphetNet + syn. mask + localness BLEU-4 24.37 # 5
METEOR 26.26 # 4
ROUGE-L 52.77 # 2

Methods