CVApr 11, 2017

Creativity: Generating Diverse Questions using Variational Autoencoders

arXiv:1704.03493v1159 citations
AI Analysis

This addresses the need for creative question generation in computational domains, though it appears incremental as it builds on existing VAE and LSTM methods.

The paper tackled the problem of generating diverse questions from images for applications in education, entertainment, and AI assistants, and the result was a framework that combines variational autoencoders with LSTM networks to produce a large set of varying questions from a single input image.

Generating diverse questions for given images is an important task for computational education, entertainment and AI assistants. Different from many conventional prediction techniques is the need for algorithms to generate a diverse set of plausible questions, which we refer to as "creativity". In this paper we propose a creative algorithm for visual question generation which combines the advantages of variational autoencoders with long short-term memory networks. We demonstrate that our framework is able to generate a large set of varying questions given a single input image.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes