@inproceedings{huang2019hierarchically,
author = {Huang, Qiuyuan and Gan, Zhe and Celikyilmaz, Asli and Wu, Oliver and Wang, Jianfeng and He, Xiaodong},
title = {Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation},
booktitle = {AAAI 2019},
year = {2019},
month = {January},
abstract = {We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a flat deep reinforcement learning baseline.},
url = {http://approjects.co.za/?big=en-us/research/publication/hierarchically-structured-reinforcement-learning-topically-coherent-visual-story-generation-2/},
}