Stronger Transformers for Neural Multi-Hop Question Generation
arXiv:2010.11374
Abstract
Prior work on automated question generation has almost exclusively focused on generating simple questions whose answers can be extracted from a single document. However, there is an increasing interest in developing systems that are capable of more complex multi-hop question generation, where answering the questions requires reasoning over multiple documents. In this work, we introduce a series of strong transformer models for multi-hop question generation, including a graph-augmented transformer that leverages relations between entities in the text. While prior work has emphasized the importance of graph-based models, we show that we can substantially outperform the state-of-the-art by 5 BLEU points using a standard transformer architecture. We further demonstrate that graph-based augmentations can provide complimentary improvements on top of this foundation. Interestingly, we find that several important factors--such as the inclusion of an auxiliary contrastive objective and data filtering could have larger impacts on performance. We hope that our stronger baselines and analysis provide a constructive foundation for future work in this area.
Code will be made available
References in corpus (13)
- Semi-Supervised Classification with Graph Convolutional Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Variational Reasoning for Question Answering with Knowledge Graph
- Question Answering and Question Generation as Dual Tasks
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Learning Data Manipulation for Augmentation and Weighting
- Multi-hop Question Answering via Reasoning Chains
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
- Differentiable Reasoning over a Virtual Knowledge Base
- Question Generation from Paragraphs: A Tale of Two Hierarchical Models
- Graph Sequential Network for Reasoning over Sequences