arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.14657cs.CVcs.MM
收藏

面向直播视频评论生成的知识增强模型

Knowledge Enhanced Model for Live Video Comment Generation

Renmin University of China(中国人民大学);Columbia University(哥伦比亚大学)

Jieting Chen, Junkai Ding, Wenping Chen, Qin Jin

AI总结:

针对现有直播视频评论生成研究忽略长视频的问题,本文构建了MovieLC长视频直播评论数据集,提出融入外部知识的预训练编解码知识增强生成模型,经实验验证有效,相关数据和代码将开源。

摘要:

直播视频评论在视频媒体平台广受欢迎,它能营造聊天氛围,为用户观看视频时提供补充信息。自动生成直播视频评论可提升用户体验,还能为机器人聊天实现类人生成。现有研究大多聚焦短视频数据集,却忽略了电影这类长视频等其他重要视频类型。本研究中,我们收集了全新的Movie Live Comments(MovieLC,电影直播评论)数据集,以支撑长视频直播评论生成的研究。受直播视频评论发散性、信息丰富的特性启发,我们还提出了一种知识增强生成模型。该模型采用预训练编码器-解码器框架,并融入外部知识。大量实验表明,客观指标与人工评估均验证了所提模型的有效性。MovieLC数据集及我们的代码将会公开发布。

英文摘要:

Live video commenting is popular on video media platforms, as it can create a chatting atmosphere and provide supplementary information for users while watching videos. Automatically generating live video comments can improve user experience and enable human-like generation for bot chatting. Existing works mostly focus on short video datasets while ignoring other important video types such as long videos like movies. In this work, we collect a new Movie Live Comments (MovieLC) dataset to support research on live video comment generation for long videos. We also propose a knowledge enhanced generation model inspired by the divergent and informative nature of live video comments. Our model adopts a pre-training encoder-decoder framework and incorporates external knowledge. Extensive experiments show that both objective metrics and human evaluation demonstrate the effectiveness of our proposed model. The MovieLC dataset and our code will be released.

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。

↑