pith. sign in

arxiv: 1805.08191 · v3 · pith:7C4ZBCOVnew · submitted 2018-05-21 · 💻 cs.CV · cs.AI· cs.LG· cs.NE

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation

classification 💻 cs.CV cs.AIcs.LGcs.NE
keywords learningreinforcementdecodergeneratinghierarchicallystructuredvisualcoherent
0
0 comments X
read the original 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 from both automatic and human evaluations demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WriterForcing: Generating more interesting story endings

    cs.LG 2019-07 unverdicted novelty 4.0

    WriterForcing combines keyphrase attention and non-generic word promotion in Seq2Seq models to produce more diverse and interesting story endings.