arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.02401cs.CL
收藏

视觉引导的生成式预训练语言模型多模态摘要自动生成

Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization

Center for Artificial Intelligence Research (CAiRE)(人工智能研究中心(CAiRE));Department of Electronic and Computer Engineering(电子与计算机工程系);The Hong Kong University of Science and Technology(香港科技大学)

Tiezheng Yu, Wenliang Dai, Zihan Liu, Pascale Fung

摘要:

多模态摘要(MultimodalAbstractiveSummarization,MAS)模型能够从互联网上的海量多模态数据中提取关键信息。最近,大规模生成预训练语言模型(GPLM)已被证明是有效的文本生成任务。然而,现有的MAS模型不能利用GPLM强大的生成能力。为了填补这一研究空白,我们的目标是研究两个研究问题:1)如何将视觉信息注入到GPLM中,而不损害他们的生成能力; 2)在GPLM中的最佳位置是注入视觉信息。在本文中,我们提出了一个简单而有效的方法来构建视觉引导(VG)GPLM的MAS任务使用基于注意力的附加层,将视觉信息,同时保持其原始文本生成能力。结果表明,我们的最佳模型在How2数据集上的5.7 ROUGE-1,5.3 ROUGE-2和5.1 ROUGE-L得分显着超过了现有的最先进的模型,我们的视觉引导方法贡献了83.6%的整体改进。此外,我们进行了全面的消融研究,以分析各种模态融合方法和融合位置的有效性。

英文摘要:

Multimodal abstractive summarization (MAS) models that summarize videos (vision modality) and their corresponding transcripts (text modality) are able to extract the essential information from massive multimodal data on the Internet. Recently, large-scale generative pre-trained language models (GPLMs) have been shown to be effective in text generation tasks. However, existing MAS models cannot leverage GPLMs' powerful generation ability. To fill this research gap, we aim to study two research questions: 1) how to inject visual information into GPLMs without hurting their generation ability; and 2) where is the optimal place in GPLMs to inject the visual information? In this paper, we present a simple yet effective method to construct vision guided (VG) GPLMs for the MAS task using attention-based add-on layers to incorporate visual information while maintaining their original text generation ability. Results show that our best model significantly surpasses the prior state-of-the-art model by 5.7 ROUGE-1, 5.3 ROUGE-2, and 5.1 ROUGE-L scores on the How2 dataset, and our visual guidance method contributes 83.6% of the overall improvement. Furthermore, we conduct thorough ablation studies to analyze the effectiveness of various modality fusion methods and fusion locations.

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。

↑