Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling

02/05/2021
by   Hong Chen, et al.
4

Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a generated story by using a concept selection module that suggests a set of concept candidates. Then, we utilize a large scale pre-trained model to convert concepts and images into full stories. To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed. To obtain appropriate concepts from the graph, we propose two novel modules that consider the correlation among candidate concepts and the image-concept correlation. Extensive automatic and human evaluation results demonstrate that our model can produce reasonable concepts. This enables our model to outperform the previous models by a large margin on the diversity and informativeness of the story, while retaining the relevance of the story to the image sequence.

READ FULL TEXT

page 1

page 2

page 3

page 7

page 8

11/01/2018

Incorporating Structured Commonsense Knowledge in Story Completion

The ability to select an appropriate story ending is the first step towa...
08/19/2022

UnCommonSense: Informative Negative Knowledge about Everyday Concepts

Commonsense knowledge about everyday concepts is an important asset for ...
12/19/2019

Discriminative Sentence Modeling for Story Ending Prediction

Story Ending Prediction is a task that needs to select an appropriate en...
12/12/2021

Contextualized Scene Imagination for Generative Commonsense Reasoning

Humans use natural language to compose common concepts from their enviro...
05/30/2018

Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling

Visual storytelling includes two important parts: coherence between the ...
10/21/2021

Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization

While much research has been done in text-to-image synthesis, little wor...
12/27/2020

SMART: A Situation Model for Algebra Story Problems via Attributed Grammar

Solving algebra story problems remains a challenging task in artificial ...