Abstract: Video transcript summarization is a fundamental task for video understanding.
Conventional approaches for transcript summarization are usually built upon the
summarization data for written language such as news articles, while the domain
discrepancy may degrade the model performance on spoken text. In this paper, we
present VT-SSum, a benchmark dataset with spoken language for video transcript
segmentation and summarization, which includes 125K transcript-summary pairs
from 9,616 videos. VT-SSum takes advantage of the videos from VideoLectures.NET
by leveraging the slides content as the weak supervision to generate the
extractive summary for video transcripts. Experiments with a state-of-the-art
deep learning approach show that the model trained with VT-SSum brings a
significant improvement on the AMI spoken text summarization benchmark. VT-SSum
will be publicly available to support the future research of video transcript
segmentation and summarization tasks.