Knowledge Enhanced Model for Live Video Comment Generation
This work addresses the challenge of live video comment generation for long videos, which is incremental as it extends existing methods to a new dataset type.
The authors tackled the problem of generating live video comments for long videos by collecting a new Movie Live Comments dataset and proposing a knowledge-enhanced generation model, achieving effectiveness demonstrated by both objective metrics and human evaluation.
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.