Multi-hop Question Generation with Graph Convolutional Network

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4636–4647 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4636 Multi-hop Question Generation with Graph Convolutional Network Dan Su, Yan Xu, Wenliang Dai, Ziwei Ji, Tiezheng Yu, Pascale Fung Center for Artificial Intelligence Research (CAiRE) Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong {dsu, yxucb, wdaiai, zjiad, tyuah}@connect.ust.hk, pascale@ece.ust.hk Abstract Multi-hop Question Generation (QG) aims to generate answer-related questions by aggre- gating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task com- pared to conventional single-hop QG, where the questions are generated from the sentence containing the answer or nearby sentences in the same paragraph without complex reason- ing. To address the additional challenges in multi-hop QG, we propose Multi-Hop En- coding Fusion Network for Question Genera- tion (MulQG), which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate. To the best of our knowl- edge, we are the first to tackle the challenge of multi-hop reasoning over paragraphs with- out any sentence-level information. Empiri- cal results on HotpotQA dataset demonstrate the effectiveness of our method, in comparison with baselines on automatic evaluation metrics. Moreover, from the human evaluation, our pro- posed model is able to generate fluent ques- tions with high completeness and outperforms the strongest baseline by 20.8% in the multi- hop evaluation. The code is publicly available at https://github.com/HLTCHKUST/MulQG. 1 Introduction Question Generation (QG) is a task to automati- cally generate a question from a given context and, optionally, an answer. Recently, we have observed an increasing interest in text-based QG (Du et al., 2017; Zhao et al., 2018; Scialom et al., 2019; Nema et al., 2019; Zhang and Bansal, 2019). Most of the existing works on text-based QG focus on generating SQuAD-style (Rajpurkar et al., 2016; Puri et al., 2020) questions, which are gen- erated from the sentence containing the answer or nearby sentences in the same paragraph, via Paragraph A: Marine Tactical Air Command Squadron 28 (Location T) is a United States Marine Corps aviation command and control unit based at Marine Corps Air Station Cherry Point (Location C) ... Paragraph B: Marine Corps Air Station Cherry Point (Location C) ... is a United States Marine Corps airfield located in Havelock, North Car- olina (Location H), USA ... Answer: Havelock, North Carolina (Location H) Question: What city is the Marine Air Control Group 28 (Location T) located in? Table 1: An example of multi-hop QG in the Hot- potQA (Yang et al., 2018) dataset. Given the answer is Location H, to ask where is T located, the model needs a bridging evidence to know that T is located in C, and C is located in H (T → C → H). This is done by multi-hop reasoning. single-hop reasoning (Zhou et al., 2017; Zhao et al., 2018). Little effort has been put in multi-hop QG, …

Content truncated to 500 words