In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance. The dataset, repository, and models will be publicly available to facilitate further research on this new task.
Cite
@article{arxiv.2209.00068,
title = {Incorporating Task-specific Concept Knowledge into Script Learning},
author = {Chenkai Sun and Tie Xu and ChengXiang Zhai and Heng Ji},
journal= {arXiv preprint arXiv:2209.00068},
year = {2023}
}