MultiQG-TI: Towards Question Generation from Multi-modal Sources

Zichao Wang, Richard G. Baraniuk

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

2 Scopus citations

Abstract

We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources. We propose a simple solution for our new problem, called MultiQG-TI, which enables a text-only question generator to process visual input in addition to textual input. Specifically, we leverage an image-to-text model and an optical character recognition model to obtain the textual description of the image and extract any texts in the image, respectively, and then feed them together with the input texts to the question generator. We only fine-tune the question generator while keeping the other components fixed. On the challenging ScienceQA dataset, we demonstrate that MultiQG-TI significantly outperforms ChatGPT with few-shot prompting, despite having hundred-times less trainable parameters. Additional analyses empirically confirm the necessity of both visual and textual signals for QG and show the impact of various modeling choices. Code is available at https://rb.gy/020tw.

Original languageEnglish (US)
Title of host publicationBEA 2023 - 18th Workshop on Innovative Use of NLP for Building Educational Applications, Proceedings of the Workshop
EditorsEkaterina Kochmar, Jill Burstein, Andrea Horbach, Andrea Horbach, Andrea Horbach, Ronja Laarmann-Quante, Nitin Madnani, Anais Tack, Victoria Yaneva, Zheng Yuan, Torsten Zesch, Torsten Zesch
PublisherAssociation for Computational Linguistics (ACL)
Pages682-691
Number of pages10
ISBN (Electronic)9781959429807
StatePublished - 2023
Event18th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2023 - Toronto, Canada
Duration: Jul 13 2023 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference18th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2023
Country/TerritoryCanada
CityToronto
Period7/13/23 → …

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'MultiQG-TI: Towards Question Generation from Multi-modal Sources'. Together they form a unique fingerprint.

Cite this