Difficulty-controllable multi-hop question generation from knowledge graphs

Vishwajeet Kumar, Yuncheng Hua, Ganesh Ramakrishnan, Guilin Qi, Lianli Gao, Yuan Fang Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

12 Citations (Scopus)


Knowledge graphs have become ubiquitous data sources and their utility has been amplified by the research on ability to answer carefully crafted questions over knowledge graphs. We investigate the problem of question generation (QG) over knowledge graphs wherein, the level of difficulty of the question can be controlled. We present an end-to-end neural network-based method for automatic generation of complex multi-hop questions over knowledge graphs. Taking a subgraph and an answer as input, our transformer-based model generates a natural language question. Our model incorporates difficulty estimation based on named entity popularity, and makes use of this estimation to generate difficulty-controllable questions. We evaluate our model on two recent multi-hop QA datasets. Our evaluation shows that our model is able to generate high-quality, fluent and relevant questions. We have released our curated QG dataset and code at https://github.com/liyuanfang/mhqg.

Original languageEnglish
Title of host publicationThe Semantic Web – ISWC 2019
Subtitle of host publication18th International Semantic Web Conference Auckland, New Zealand, October 26–30, 2019 Proceedings, Part I
EditorsChiara Ghidini, Olaf Hartig, Maria Maleshkova, Vojtech Svátek, Isabel Cruz, Aidan Hogan, Jie Song, Maxime Lefrançois, Fabien Gandon
Place of PublicationCham Switzerland
Number of pages17
ISBN (Electronic)9783030307936
ISBN (Print)9783030307929
Publication statusPublished - 2019
EventInternational Semantic Web Conference 2019 - Auckland, New Zealand
Duration: 26 Oct 201930 Oct 2019
Conference number: 18th

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceInternational Semantic Web Conference 2019
Abbreviated titleISWC 2019
Country/TerritoryNew Zealand
Internet address


  • Knowledge graph
  • Natural language processing
  • Neural network
  • Question generation
  • Transformer

Cite this