arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.03749cs.CV
收藏

通过序列级探索改善字幕

Better Captioning with Sequence-Level Exploration

Carnegie Mellon University(卡内基梅隆大学);Renmin University of China(中国人民大学);Language Technology Institute(语言技术研究所);School of Information(信息学院)

Jia Chen, Qin Jin

摘要:

序列级学习目标已被广泛应用于字幕任务中,以实现许多模型的最新性能。在这个目标中,模型通过其生成的字幕的质量(序列级)的奖励来训练。在这项工作中,我们从理论和实证结果表明,目前的字幕任务的序列级学习目标的局限性。从理论上讲,我们证明了当前的目标相当于只优化了模型生成的字幕集的精度方面,因此忽略了召回方面。实验结果表明,该目标训练的模型在召回方面往往得到较低的分数。我们建议在当前目标中添加序列级探索项以提高召回率。它引导模型在训练中探索更合理的标题。通过这种方式,所提出的目标同时考虑了生成的字幕的精确度和召回率。实验结果表明,该方法在视频和图像描述数据集上的有效性。

英文摘要:

Sequence-level learning objective has been widely used in captioning tasks to achieve the state-of-the-art performance for many models. In this objective, the model is trained by the reward on the quality of its generated captions (sequence-level). In this work, we show the limitation of the current sequence-level learning objective for captioning tasks from both theory and empirical result. In theory, we show that the current objective is equivalent to only optimizing the precision side of the caption set generated by the model and therefore overlooks the recall side. Empirical result shows that the model trained by this objective tends to get lower score on the recall side. We propose to add a sequence-level exploration term to the current objective to boost recall. It guides the model to explore more plausible captions in the training. In this way, the proposed objective takes both the precision and recall sides of generated captions into account. Experiments show the effectiveness of the proposed method on both video and image captioning datasets.

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。

↑