GraphPlan: Story Generation by Planning with Event Graph
This work aims to improve the logical coherence of automatically generated stories for general users, which is an incremental improvement over existing story generation techniques.
The paper addresses the challenge of generating meaningful stories with logical correctness by planning event sequences using automatically constructed event graphs. Human evaluation indicates that their approach produces more logically correct event sequences and stories compared to existing methods.
Story generation is a task that aims to automatically produce multiple sentences to make up a meaningful story. This task is challenging because it requires high-level understanding of semantic meaning of sentences and causality of story events. Naive sequence-to-sequence models generally fail to acquire such knowledge, as the logical correctness can hardly be guaranteed in a text generation model without the strategic planning. In this paper, we focus on planning a sequence of events assisted by event graphs, and use the events to guide the generator. Instead of using a sequence-to-sequence model to output a storyline as in some existing works, we propose to generate an event sequence by walking on an event graph. The event graphs are built automatically based on the corpus. To evaluate the proposed approach, we conduct human evaluation both on event planning and story generation. Based on large-scale human annotation results, our proposed approach is shown to produce more logically correct event sequences and stories.