# WriterForcing: Generating more interesting story endings

## TL;DR

This paper introduces models that generate more diverse and engaging story endings by focusing on key story elements and encouraging the use of non-generic words, addressing the limitations of traditional Seq2Seq models.

## Contribution

The paper proposes a novel approach combining keyphrase attention and non-generic word promotion to improve story ending diversity and interest.

## Key findings

- Generated endings are more diverse and engaging.
- Models outperform baseline Seq2Seq in diversity metrics.
- Endings show increased relevance to story context.

## Abstract

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.