CLSEG: Contrastive Learning of Story Ending Generation

TL;DR

This paper introduces CLSEG, a contrastive learning framework that improves story ending generation by enhancing the consistency and rationality of generated endings through novel sampling and training strategies.

Contribution

It proposes a novel contrastive learning approach with multi-aspect sampling and story-specific strategies for more coherent story ending generation.

Findings

CLSEG outperforms baseline models in experiments.

Generated endings show improved consistency and rationality.

The method effectively models story context and ending coherence.

Abstract

Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However, the pre-training objective of PLM-based methods is unable to model the consistency between story context and ending. The goal of this paper is to adopt contrastive learning to generate endings more consistent with story context, while there are two main challenges in contrastive learning of SEG. First is the negative sampling of wrong endings inconsistent with story contexts. The second challenge is the adaptation of contrastive learning for SEG. To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning. Particularly, for the first issue, we utilize novel multi-aspect sampling mechanisms to obtain wrong endings considering the consistency of order, causality, and sentiment. To solve the second issue, we well-design a story-specific contrastive training strategy that is adapted for SEG. Experiments show that CLSEG outperforms baselines and can produce story endings with stronger consistency and rationality.