CLSEG: Contrastive Learning of Story Ending Generation
This addresses a specific challenge in natural language generation for story completion, though it appears incremental as it builds on existing PLM-based methods.
The paper tackles the problem of generating story endings that are consistent with story context in Story Ending Generation (SEG), proposing CLSEG, a contrastive learning framework that uses multi-aspect sampling and story-specific training to improve consistency, with experiments showing it outperforms baselines in producing more consistent and rational endings.
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.