Knowledge Enhanced Model for Live Video Comment Generation

TL;DR

This paper introduces a new dataset and a knowledge-enhanced model for generating live video comments, especially tailored for long videos like movies, improving user interaction and chat quality.

Contribution

The work presents a novel MovieLC dataset for long videos and a knowledge-enhanced generation model that leverages external information for more engaging comments.

Findings

The proposed model outperforms baselines on objective metrics.

Human evaluation confirms improved comment quality.

The MovieLC dataset supports research on long video comment generation.

Abstract

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.