Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling
Abstract
Visual storytelling includes two important parts: coherence between the story and images as well as the story structure. For image to text neural network models, similar images in the sequence would provide close information for story generator to obtain almost identical sentence. However, repeatedly narrating same objects or events will undermine a good story structure. In this paper, we proposed an inter-sentence diverse beam search to generate a more expressive story. Comparing to some recent models of visual storytelling task, which generate story without considering the generated sentence of the previous picture, our proposed method can avoid generating identical sentence even given a sequence of similar pictures.
Keywords
Cite
@article{arxiv.1805.11867,
title = {Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling},
author = {Chao-Chun Hsu and Szu-Min Chen and Ming-Hsun Hsieh and Lun-Wei Ku},
journal= {arXiv preprint arXiv:1805.11867},
year = {2018}
}
Comments
Challenge paper in storytelling workshop co-located with NAACL 2018