Distractor generation with generative adversarial nets for automatically creating fill-in-the-blank questions

Chen Liang, Xiao Yang, Drew Wham, Bart Pursel, Rebecca Passonneau, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations


Distractor generation is a crucial step for fill-in-the-blank question generation. We propose a generative model learned from training generative adversarial nets (GANs) to create useful distractors. Our method utilizes only context information and does not use the correct answer, which is completely different from previous Ontologybased or similarity-based approaches. Trained on the Wikipedia corpus, the proposed model is able to predict Wiki entities as distractors. Our method is evaluated on two biology question datasets collected from Wikipedia and actual college-level exams. Experimental results show that our context-based method achieves comparable performance to a frequently used word2vec-based method for the Wiki dataset. In addition, we propose a second-stage learner to combine the strengths of the two methods, which further improves the performance on both datasets, with 51.7% and 48.4% of generated distractors being acceptable.

Original languageEnglish (US)
Title of host publicationProceedings of the Knowledge Capture Conference, K-CAP 2017
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450355537
StatePublished - Dec 4 2017
Event9th International Conference on Knowledge Capture, K-CAP 2017 - Austin, United States
Duration: Dec 4 2017Dec 6 2017

Publication series

NameProceedings of the Knowledge Capture Conference, K-CAP 2017


Other9th International Conference on Knowledge Capture, K-CAP 2017
CountryUnited States

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Software
  • Computer Science Applications
  • Information Systems

Cite this