Learning to Encode Evolutionary Knowledge for Automatic Commenting Long Novels
This addresses the challenge of understanding and generating text for dynamic, long-form narratives, which is an incremental advancement in knowledge graph-based text generation.
The paper tackles the problem of automatically generating comments for long novels by modeling dynamic storylines, proposing an Evolutionary Knowledge Graph (EKG) to capture character and relation transitions, and achieves superior performance over strong baselines in evaluations.
Static knowledge graph has been incorporated extensively into sequence-to-sequence framework for text generation. While effectively representing structured context, static knowledge graph failed to represent knowledge evolution, which is required in modeling dynamic events. In this paper, an automatic commenting task is proposed for long novels, which involves understanding context of more than tens of thousands of words. To model the dynamic storyline, especially the transitions of the characters and their relations, Evolutionary Knowledge Graph(EKG) is proposed and learned within a multi-task framework. Given a specific passage to comment, sequential modeling is used to incorporate historical and future embedding for context representation. Further, a graph-to-sequence model is designed to utilize the EKG for comment generation. Extensive experimental results show that our EKG-based method is superior to several strong baselines on both automatic and human evaluations.