arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01764cs.CLcs.AIcs.HC
收藏

视觉故事后期编辑

Visual Story Post-Editing

Pennsylvania State University(宾夕法尼亚州立大学);Carnegie Mellon University(卡内基梅隆大学)

Ting-Yao Hsu, Chieh-Yang Huang, Yen-Chia Hsu, Ting-Hao 'Kenneth' Huang

摘要:

我们介绍了第一个数据集的人工编辑机器生成的视觉故事,并探讨如何收集这些编辑可用于视觉故事后编辑任务。VIST-Edit数据集包括2,981个机器生成的视觉故事的14,905个人工编辑版本。这些故事是由两个最先进的视觉故事模型生成的,每个模型都与5个人工编辑的版本相匹配。我们为任务建立了基线,展示了如何利用相对较小的一组人类编辑来提高大型视觉故事模型的性能。我们还讨论了自动评估分数和人类评级之间的弱相关性,激励需要新的自动度量。

英文摘要:

We introduce the first dataset for human edits of machine-generated visual stories and explore how these collected edits may be used for the visual story post-editing task. The dataset, VIST-Edit, includes 14,905 human edited versions of 2,981 machine-generated visual stories. The stories were generated by two state-of-the-art visual storytelling models, each aligned to 5 human-edited versions. We establish baselines for the task, showing how a relatively small set of human edits can be leveraged to boost the performance of large visual storytelling models. We also discuss the weak correlation between automatic evaluation scores and human ratings, motivating the need for new automatic metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑