Returning to the Start: Generating Narratives with Related Endpoints
This addresses the challenge of creating coherent and satisfying narratives in AI story generation, though it is incremental in focusing on endpoint relationships.
The paper tackles the problem of generating narratives with satisfying closure by ensuring first and last sentences are related, proposing RENarGen, which outperforms autoregressive models in producing better stories with more narrative closure.
Human writers often bookend their writing with ending sentences that relate back to the beginning sentences in order to compose a satisfying narrative that "closes the loop." Motivated by this observation, we propose RENarGen, a controllable story-generation paradigm that generates narratives by ensuring the first and last sentences are related and then infilling the middle sentences. Our contributions include an initial exploration of how various methods of bookending from Narratology affect language modeling for stories. Automatic and human evaluations indicate RENarGen produces better stories with more narrative closure than current autoregressive models.