• Home
  • Search
  • Difficulty-Controllable Visual Question Generation
  • Cite Icon8
  • https://doi.org/10.1007/978-3-030-85896-4_26Copy DOI Icon

Difficulty-Controllable Visual Question Generation

  • Jan 1, 2021
  • Feng Chen +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Visual Question Generation (VQG) aims to generate questions from images. Existing studies on this topic focus on generating questions solely based on images while neglecting the difficulty of questions. However, to engage users, an automated question generator should produce questions with a level of difficulty that are tailored to a user’s capabilities and experience. In this paper, we propose a Difficulty-controllable Generation Network (DGN) to alleviate this limitation. We borrow difficulty index from education area to define a difficulty variable for representing the difficulty of questions, and fuse it into our model to guide the difficulty-controllable question generation. Experimental results demonstrate that our proposed model not only achieves significant improvements on several automatic evaluation metrics, but also can generate difficulty-controllable questions.

Similar Papers
  • Research Article
  • Citations4

Comparison of template-based and multilayer perceptron-based approach for automatic question generation system

  • Dec 01, 2022
  • Indonesian Journal of Electrical Engineering and Computer Science
  • Walelign Tewabe Sewunetie +1
  • PDF
  • Research Article
  • Citations91

A Survey on Evaluation Metrics for Machine Translation

  • Feb 16, 2023
  • Mathematics
  • Seungjun Lee +7
  • Research Article
  • Citations6

A comparative analysis of lexical-based automatic evaluation metrics for different Indic language pairs

  • Feb 02, 2024
  • Journal of Autonomous Intelligence
  • Kiranjeet Kaur +1
  • Research Article
  • Citations3

Evaluating Medical Text Summaries Using Automatic Evaluation Metrics and LLM-as-a-Judge Approach: A Pilot Study

  • Dec 19, 2025
  • Diagnostics
  • Yuriy Vasilev +8
  • PDF
  • Conference Article
  • Citations32

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

  • Jan 01, 2021
  • Ananya B Sai +4
  • Video Transcripts

Perturbation CheckLists for Evaluating NLG Evaluation Metrics

  • Oct 15, 2021
  • Underline Science Inc.
  • Ananya B Sai +4
  • Conference Article
  • Citations329

ORANGE

  • Jan 01, 2004
  • Chin-Yew Lin +1
  • Conference Article
  • Citations14

On choosing an effective automatic evaluation metric for microblog summarisation

  • Aug 26, 2014
  • Stuart Mackie +3
  • PDF
  • Research Article
  • Citations25

A Framework for Word Embedding Based Automatic Text Summarization and Evaluation

  • Jan 31, 2020
  • Information
  • Tulu Tilahun Hailu +2
  • Research Article
  • Citations8

Controlled Translation in an Example-based Environment: What do Automatic Evaluation Metrics Tell Us?

  • Mar 01, 2005
  • Machine Translation
  • Andy Way +1
  • Video Transcripts

Reinforced Multi-task Approach for Multi-hop Question Generation

  • Nov 25, 2020
  • Underline Science Inc.
  • Akella Ravi Tej +4
  • PDF
  • Conference Article
  • Citations20

Reinforced Multi-task Approach for Multi-hop Question Generation

  • Jan 01, 2020
  • Deepak Gupta +4
  • PDF
  • Conference Article
  • Citations8

A Tutorial on Evaluation Metrics used in Natural Language Generation

  • Jan 01, 2021
  • Mitesh M Khapra +1
  • Research Article
  • Citations19

Significance tests of automatic machine translation evaluation metrics

  • Mar 01, 2010
  • Machine Translation
  • Ying Zhang +1
  • Book Chapter
  • Citations1

Human Versus Automatic Evaluation of NMT for Low-Resource Indian Language

  • Jan 01, 2023
  • Goutam Datta +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.