WriterForcing: Generating more interesting story endings
This addresses the issue of dull and generic endings in story generation for applications like creative writing or entertainment, though it is incremental as it builds on existing Seq2Seq methods.
The paper tackles the problem of generating interesting story endings by proposing models that focus attention on keyphrases and promote non-generic words, resulting in more diverse and interesting outputs.
We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story, multiple endings are possible. Seq2Seq models tend to ignore the context and generate generic and dull responses. Very few works have studied generating diverse and interesting story endings for a given story context. In this paper, we propose models which generate more diverse and interesting outputs by 1) training models to focus attention on important keyphrases of the story, and 2) promoting generation of non-generic words. We show that the combination of the two leads to more diverse and interesting endings.